iamzhangship commited on
Commit
9813267
·
verified ·
1 Parent(s): d750d0d

Add NeMo Conformer CTC aligner ONNX v1

Browse files
README.md ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: onnxruntime
3
+ pipeline_tag: automatic-speech-recognition
4
+ tags:
5
+ - onnx
6
+ - ctc
7
+ - forced-alignment
8
+ - word-timestamps
9
+ - mobile
10
+ - flutter
11
+ ---
12
+
13
+ # Fluency NeMo Conformer CTC Aligner
14
+
15
+ This repository contains the mobile-distribution assets for Fluency's English word-level forced alignment pipeline.
16
+
17
+ The model is not used as a standalone ASR decoder in the app. Whisper provides the transcript, this model provides frame-level CTC log-probabilities, and the app runs constrained CTC Viterbi to recover word timestamps.
18
+
19
+ ## Runtime Pipeline
20
+
21
+ ```text
22
+ Whisper transcript
23
+ → text normalization
24
+ → SentencePiece tokenizer
25
+ → native log-mel feature extraction
26
+ → ONNX Runtime Mobile
27
+ → constrained CTC Viterbi
28
+ → word timestamps
29
+ ```
30
+
31
+ ## Required App Assets
32
+
33
+ ```text
34
+ stt_en_conformer_ctc_small_features.onnx
35
+ metadata.json
36
+ tokenizer/tokenizer.model
37
+ tokenizer/vocab.txt
38
+ manifest.json
39
+ ```
40
+
41
+ Optional debugging assets are under `parity/`.
42
+
43
+ ## ONNX Contract
44
+
45
+ - Input `processed_signal`: `[batch, 80, feature_frames]` float32
46
+ - Input `processed_signal_length`: `[batch]` int64
47
+ - Output `log_probs`: `[batch, encoded_frames, 1025]` float32
48
+ - Output `encoded_len`: `[batch]` int64
49
+ - CTC blank id: `1024`
50
+
51
+ ## Feature Contract
52
+
53
+ - Sample rate: `16000 Hz`
54
+ - Channels: mono
55
+ - Feature type: 80-bin log-mel spectrogram
56
+ - Window size: `25 ms`
57
+ - Window stride: `10 ms`
58
+ - FFT: `512`
59
+ - Window: Hann
60
+ - Normalization: `per_feature`
61
+
62
+ The ONNX graph intentionally starts after feature extraction. Mobile clients must implement NeMo-compatible log-mel features before invoking ONNX Runtime.
63
+
64
+ ## Validation
65
+
66
+ Validated on a 375.838s video using raw Whisper `text` fields only:
67
+
68
+ - Windows checked: 7
69
+ - Segments checked: 110
70
+ - Matched words checked: 1029
71
+ - PyTorch feature+model total: 3.106s
72
+ - ONNX model total: 5.396s
73
+ - Log-prob mean abs diff: 0.000014
74
+ - Word center delta p50/p95/max: 0.0ms / 0.0ms / 0.0ms
75
+
76
+ See `parity/parity_1gzKSyOBpZg.json` and `parity/parity_1gzKSyOBpZg.csv` for details.
77
+
78
+ ## Download URLs
79
+
80
+ ```text
81
+ https://huggingface.co/iamzhangship/fluency-nemo-conformer-ctc-aligner/resolve/main/stt_en_conformer_ctc_small_features.onnx
82
+ https://huggingface.co/iamzhangship/fluency-nemo-conformer-ctc-aligner/resolve/main/metadata.json
83
+ https://huggingface.co/iamzhangship/fluency-nemo-conformer-ctc-aligner/resolve/main/tokenizer/tokenizer.model
84
+ https://huggingface.co/iamzhangship/fluency-nemo-conformer-ctc-aligner/resolve/main/tokenizer/vocab.txt
85
+ https://huggingface.co/iamzhangship/fluency-nemo-conformer-ctc-aligner/resolve/main/manifest.json
86
+ ```
87
+
88
+ ## Checksums
89
+
90
+ - ONNX sha256: `8998fd44bc2374c7d085f7c709fbfbd28ea6db09998622077071faf478db24fd`
91
+ - ONNX size: `53197388` bytes
92
+
93
+ Use `manifest.json` for full file sizes and sha256 checksums.
94
+
95
+ ## Source Model
96
+
97
+ - NeMo pretrained model: `stt_en_conformer_ctc_small`
98
+ - Export graph: Conformer encoder + CTC projection/log-softmax
99
+ - Export metadata model bytes: `53197388`
manifest.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "repoId": "iamzhangship/fluency-nemo-conformer-ctc-aligner",
3
+ "createdAt": "2026-07-07T01:35:00.724077+00:00",
4
+ "version": "v1",
5
+ "modelId": "nemo-conformer-ctc-small-aligner",
6
+ "runtime": "onnxruntime",
7
+ "requiredAssets": [
8
+ "stt_en_conformer_ctc_small_features.onnx",
9
+ "metadata.json",
10
+ "tokenizer/tokenizer.model",
11
+ "tokenizer/vocab.txt"
12
+ ],
13
+ "files": {
14
+ "README.md": {
15
+ "bytes": 2908,
16
+ "sha256": "e39758b7055fdf46c013a3e3e80373f833adc37914aa1d81e07417616d198f6e",
17
+ "url": "https://huggingface.co/iamzhangship/fluency-nemo-conformer-ctc-aligner/resolve/main/README.md",
18
+ "mirrorUrl": "https://hf-mirror.com/iamzhangship/fluency-nemo-conformer-ctc-aligner/resolve/main/README.md"
19
+ },
20
+ "metadata.json": {
21
+ "bytes": 2326,
22
+ "sha256": "dbde5ff752ed8800c301bcca249996be9644ea72c8d69275c6a126ea36817a27",
23
+ "url": "https://huggingface.co/iamzhangship/fluency-nemo-conformer-ctc-aligner/resolve/main/metadata.json",
24
+ "mirrorUrl": "https://hf-mirror.com/iamzhangship/fluency-nemo-conformer-ctc-aligner/resolve/main/metadata.json"
25
+ },
26
+ "parity/parity_1gzKSyOBpZg.csv": {
27
+ "bytes": 11549,
28
+ "sha256": "31cb2ecb1692e458d0196395d6bbd543b88ceb81fd55605af3ec7edb2279675b",
29
+ "url": "https://huggingface.co/iamzhangship/fluency-nemo-conformer-ctc-aligner/resolve/main/parity/parity_1gzKSyOBpZg.csv",
30
+ "mirrorUrl": "https://hf-mirror.com/iamzhangship/fluency-nemo-conformer-ctc-aligner/resolve/main/parity/parity_1gzKSyOBpZg.csv"
31
+ },
32
+ "parity/parity_1gzKSyOBpZg.json": {
33
+ "bytes": 210384,
34
+ "sha256": "09488a722e2c0e83294b0d928b6a7161f8b5b8ca1bef6b4634b2bdd7bc91f19a",
35
+ "url": "https://huggingface.co/iamzhangship/fluency-nemo-conformer-ctc-aligner/resolve/main/parity/parity_1gzKSyOBpZg.json",
36
+ "mirrorUrl": "https://hf-mirror.com/iamzhangship/fluency-nemo-conformer-ctc-aligner/resolve/main/parity/parity_1gzKSyOBpZg.json"
37
+ },
38
+ "stt_en_conformer_ctc_small_features.onnx": {
39
+ "bytes": 53197388,
40
+ "sha256": "8998fd44bc2374c7d085f7c709fbfbd28ea6db09998622077071faf478db24fd",
41
+ "url": "https://huggingface.co/iamzhangship/fluency-nemo-conformer-ctc-aligner/resolve/main/stt_en_conformer_ctc_small_features.onnx",
42
+ "mirrorUrl": "https://hf-mirror.com/iamzhangship/fluency-nemo-conformer-ctc-aligner/resolve/main/stt_en_conformer_ctc_small_features.onnx"
43
+ },
44
+ "tokenizer/model_config.yaml": {
45
+ "bytes": 14797,
46
+ "sha256": "a1c10a149592519fe830de4e3ccb08102adbc947524892846c159246074879c5",
47
+ "url": "https://huggingface.co/iamzhangship/fluency-nemo-conformer-ctc-aligner/resolve/main/tokenizer/model_config.yaml",
48
+ "mirrorUrl": "https://hf-mirror.com/iamzhangship/fluency-nemo-conformer-ctc-aligner/resolve/main/tokenizer/model_config.yaml"
49
+ },
50
+ "tokenizer/tokenizer.model": {
51
+ "bytes": 260411,
52
+ "sha256": "d9b04033136c5d0413047fe94d2f0ab6cb088d292014bb076ee1700bdac545a9",
53
+ "url": "https://huggingface.co/iamzhangship/fluency-nemo-conformer-ctc-aligner/resolve/main/tokenizer/tokenizer.model",
54
+ "mirrorUrl": "https://hf-mirror.com/iamzhangship/fluency-nemo-conformer-ctc-aligner/resolve/main/tokenizer/tokenizer.model"
55
+ },
56
+ "tokenizer/tokenizer.vocab": {
57
+ "bytes": 16686,
58
+ "sha256": "0c57daaacbc37a473b529b656dacf668f9e5e40146caca654fed575db8c8c356",
59
+ "url": "https://huggingface.co/iamzhangship/fluency-nemo-conformer-ctc-aligner/resolve/main/tokenizer/tokenizer.vocab",
60
+ "mirrorUrl": "https://hf-mirror.com/iamzhangship/fluency-nemo-conformer-ctc-aligner/resolve/main/tokenizer/tokenizer.vocab"
61
+ },
62
+ "tokenizer/vocab.txt": {
63
+ "bytes": 5743,
64
+ "sha256": "1916b1428ff0586b2aaa6d5bc984d211e060cd0fca87c1a163b8fae02305fdc8",
65
+ "url": "https://huggingface.co/iamzhangship/fluency-nemo-conformer-ctc-aligner/resolve/main/tokenizer/vocab.txt",
66
+ "mirrorUrl": "https://hf-mirror.com/iamzhangship/fluency-nemo-conformer-ctc-aligner/resolve/main/tokenizer/vocab.txt"
67
+ }
68
+ }
69
+ }
metadata.json ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model": {
3
+ "name": "stt_en_conformer_ctc_small",
4
+ "source": "NVIDIA NeMo EncDecCTCModelBPE",
5
+ "onnx": "exports/models/stt_en_conformer_ctc_small_onnx/stt_en_conformer_ctc_small_features.onnx",
6
+ "onnxBytes": 53197388,
7
+ "opset": 17,
8
+ "dummyFeatureFrames": 6000
9
+ },
10
+ "audio": {
11
+ "sampleRate": 16000,
12
+ "channels": 1,
13
+ "sampleFormat": "float32 PCM in [-1, 1]"
14
+ },
15
+ "features": {
16
+ "type": "log-mel-spectrogram",
17
+ "features": 80,
18
+ "normalize": "per_feature",
19
+ "windowSizeSeconds": 0.025,
20
+ "windowStrideSeconds": 0.01,
21
+ "window": "hann",
22
+ "nFft": 512,
23
+ "log": true,
24
+ "frameSplicing": 1,
25
+ "dither": 1e-05,
26
+ "padTo": 0,
27
+ "padValue": 0.0
28
+ },
29
+ "ctc": {
30
+ "tokenizer": "SentencePiece",
31
+ "tokenCountWithoutBlank": 1024,
32
+ "tokenCountWithBlank": 1025,
33
+ "blankId": 1024,
34
+ "featureFrameStrideSeconds": 0.01,
35
+ "encoderSubsampling": 4,
36
+ "approxLogitFrameStrideSeconds": 0.04
37
+ },
38
+ "onnxContract": {
39
+ "inputs": [
40
+ {
41
+ "name": "processed_signal",
42
+ "shape": [
43
+ "batch",
44
+ 80,
45
+ "feature_frames"
46
+ ],
47
+ "dtype": "float32"
48
+ },
49
+ {
50
+ "name": "processed_signal_length",
51
+ "shape": [
52
+ "batch"
53
+ ],
54
+ "dtype": "int64"
55
+ }
56
+ ],
57
+ "outputs": [
58
+ {
59
+ "name": "log_probs",
60
+ "shape": [
61
+ "batch",
62
+ "encoded_frames",
63
+ 1025
64
+ ],
65
+ "dtype": "float32"
66
+ },
67
+ {
68
+ "name": "encoded_len",
69
+ "shape": [
70
+ "batch"
71
+ ],
72
+ "dtype": "int64"
73
+ }
74
+ ]
75
+ },
76
+ "tokenizerAssets": {
77
+ "vocab.txt": "exports/models/stt_en_conformer_ctc_small_onnx/tokenizer/vocab.txt",
78
+ "tokenizer.model": "exports/models/stt_en_conformer_ctc_small_onnx/tokenizer/tokenizer.model",
79
+ "tokenizer.vocab": "exports/models/stt_en_conformer_ctc_small_onnx/tokenizer/tokenizer.vocab",
80
+ "model_config.yaml": "exports/models/stt_en_conformer_ctc_small_onnx/tokenizer/model_config.yaml"
81
+ },
82
+ "mobileRuntimeNotes": [
83
+ "Compute features with the exact parameters above before calling ONNX.",
84
+ "Use the exported SentencePiece tokenizer; do not build a custom a-z tokenizer.",
85
+ "Run constrained CTC Viterbi in native code; do not use beam search for known transcript alignment."
86
+ ]
87
+ }
parity/parity_1gzKSyOBpZg.csv ADDED
@@ -0,0 +1,118 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ kind,windowIndex,subtitleIndex,status,pytorchSeconds,onnxSeconds,maxAbsDiff,meanAbsDiff,encodedLenPyTorch,encodedLenOnnx,centerDeltaMs,text
2
+ window,0,,matched,0.605,0.945,0.003302,1.3e-05,1501,1501,,
3
+ segment,0,0,skipped_no_alignable_words / skipped_no_alignable_words,,,,,,,, [MUSIC PLAYING]
4
+ segment,0,1,skipped_no_alignable_words / skipped_no_alignable_words,,,,,,,, [MUSIC PLAYING]
5
+ segment,0,2,skipped_no_alignable_words / skipped_no_alignable_words,,,,,,,, [MUSIC PLAYING]
6
+ segment,0,3,skipped_no_alignable_words / skipped_no_alignable_words,,,,,,,, [MUSIC PLAYING]
7
+ segment,0,4,skipped_no_alignable_words / skipped_no_alignable_words,,,,,,,, [MUSIC PLAYING]
8
+ segment,0,5,aligned / aligned,,,,,,,0.0, There is a magma chamber of anger
9
+ segment,0,6,aligned / aligned,,,,,,,0.0, sat underneath British society right now.
10
+ segment,0,7,skipped_no_alignable_words / skipped_no_alignable_words,,,,,,,, [MUSIC PLAYING]
11
+ segment,0,8,aligned / aligned,,,,,,,0.0, Britain's been shifting to the right.
12
+ segment,0,9,aligned / aligned,,,,,,,0.0, I've spent the past few months trying
13
+ segment,0,10,aligned / aligned,,,,,,,0.0, to understand what's happening in this country.
14
+ segment,0,11,aligned / aligned,,,,,,,0.0, No one speaks to the media law.
15
+ segment,0,12,aligned / aligned,,,,,,,0.0," Attending far-right protests, including United Kingdom,"
16
+ segment,0,13,aligned / aligned,,,,,,,0.0, one of the biggest far-right rallies ever
17
+ segment,0,14,aligned / aligned,,,,,,,0.0," on the streets of the UK, where tens of thousands responded"
18
+ segment,0,15,aligned / aligned,,,,,,,0.0, to the call at this man.
19
+ segment,0,16,aligned / aligned,,,,,,,0.0," Anti-Islam activist Tommy Robinson,"
20
+ segment,0,17,aligned / aligned,,,,,,,0.0, a convicted criminal turned anti-establishment figure.
21
+ segment,0,18,aligned / aligned,,,,,,,0.0, Are you ready for the battle of Britain?
22
+ segment,0,19,skipped_no_alignable_words / skipped_no_alignable_words,,,,,,,, [CHEERING]
23
+ segment,0,20,aligned / aligned,,,,,,,0.0," But it's not just on the streets,"
24
+ segment,0,21,aligned / aligned,,,,,,,0.0, and it's not just the extreme right that's on the up.
25
+ segment,0,22,aligned / aligned,,,,,,,0.0, The populist right-wing party reform UK led by longtime Trump
26
+ segment,0,23,aligned / aligned,,,,,,,0.0, online.
27
+ window,1,,matched,0.513,0.886,0.000738,1.4e-05,1501,1501,,
28
+ segment,1,24,aligned / aligned,,,,,,,0.0, The former U.K. led by longtime Trump ally Nigel Farage made massive gains in local elections in May.
29
+ segment,1,25,aligned / aligned,,,,,,,0.0, This right word shift isn't one single movement.
30
+ segment,1,26,aligned / aligned,,,,,,,0.0," The different groups represent different shades of right-wing politics,"
31
+ segment,1,27,aligned / aligned,,,,,,,0.0, but they all seem to be feeding off of a divided Britain.
32
+ segment,1,28,aligned / aligned,,,,,,,0.0, And the heart of those divisions is the issue of migration.
33
+ segment,1,29,aligned / aligned,,,,,,,0.0," Just this week, a horrific attack by a Sudanese refugee on the streets of Belfast almost immediately turned into the latest ""I told you so"" moment for the far right."
34
+ segment,1,30,aligned / aligned,,,,,,,0.0," Transforming a local tragedy into a national rallying cry, powerful allies, amplifying the message and fanning the flames of hate."
35
+ segment,1,31,aligned / aligned,,,,,,,0.0," People in Britain are angry. Joe Mulhol infiltrated far-right groups, undercover here in the U.K. and in the U.S."
36
+ segment,1,32,aligned / aligned,,,,,,,0.0, He's one of the U.K.'s top experts on these movements.
37
+ segment,1,33,aligned / aligned,,,,,,,0.0," You know, if you look at the way that people's lives have been, you know, lack of jobs, houses, schools, hospitals."
38
+ window,2,,matched,0.495,0.885,0.000626,1.2e-05,1501,1501,,
39
+ segment,2,34,aligned / aligned,,,,,,,0.0," houses, schools, hospitals, stagnated wages, living standards going down or"
40
+ segment,2,35,aligned / aligned,,,,,,,0.0, stagnating for years and years and they feel that mainstream political parties
41
+ segment,2,36,aligned / aligned,,,,,,,0.0, have not met their material needs. What the far right are really good at is
42
+ segment,2,37,aligned / aligned,,,,,,,0.0, going to those people and they turn up and they say you're right to be angry and
43
+ segment,2,38,aligned / aligned,,,,,,,0.0, they give them a scapegoat and they say it's because someone has come to this
44
+ segment,2,39,aligned / aligned,,,,,,,0.0, country and taken it from. They're really good at redirecting people's
45
+ segment,2,40,aligned / aligned,,,,,,,0.0, anger from where it should be directed. I've seen exactly what Joe's talking
46
+ segment,2,41,aligned / aligned,,,,,,,0.0, about. There have been hundreds of protests across the country over the
47
+ segment,2,42,aligned / aligned,,,,,,,0.0, past year according to activists tracking far-right movements. It's mostly been
48
+ segment,2,43,aligned / aligned,,,,,,,0.0, about migration and how consecutive governments have dealt with this issue.
49
+ segment,2,44,aligned / aligned,,,,,,,0.0," And with the center left, labor party back in power for the first time in two"
50
+ segment,2,45,aligned / aligned,,,,,,,0.0," decades, the far-right senses conditions are ripe for resurgence. It's in tight-knit"
51
+ segment,2,46,aligned / aligned,,,,,,,0.0, communities like this one in the sleepy market town of Faversham outside London
52
+ segment,2,47,aligned / aligned,,,,,,,0.0, where we saw it all play out late last year. Walking through town
53
+ window,3,,matched,0.47,0.866,0.040859,2.6e-05,1501,1501,,
54
+ segment,3,48,aligned / aligned,,,,,,,0.0," here. Walking through town with a protest organized by a far right activist, you see those divisions"
55
+ segment,3,49,aligned / aligned,,,,,,,0.0, and feel the anger.
56
+ segment,3,50,aligned / aligned,,,,,,,0.0," ""Shame on me!"""
57
+ segment,3,51,aligned / aligned,,,,,,,0.0," ""Shame on me!"""
58
+ segment,3,52,aligned / aligned,,,,,,,0.0," ""Shame on me!"""
59
+ segment,3,53,aligned / aligned,,,,,,,0.0," ""Right now, they're marching towards this facility where unaccompanied minors asylum seekers"
60
+ segment,3,54,aligned / aligned,,,,,,,0.0," have been housed in this town."""
61
+ segment,3,55,aligned / aligned,,,,,,,0.0," ""I'm straight!"""
62
+ segment,3,56,aligned / aligned,,,,,,,0.0," ""I'm straight!"""
63
+ segment,3,57,aligned / aligned,,,,,,,0.0," They're a loud crowd, but it's clear they're more noise than numbers."
64
+ segment,3,58,aligned / aligned,,,,,,,0.0, And you do see locals coming out to confront them.
65
+ segment,3,59,aligned / aligned,,,,,,,0.0," ""Hey!"
66
+ segment,3,60,aligned / aligned,,,,,,,0.0, Right there!
67
+ segment,3,61,aligned / aligned,,,,,,,0.0," Right, you two, so welcome here!"""
68
+ segment,3,62,aligned / aligned,,,,,,,0.0," The main event kicks off with a rambling mix of racist rhetoric, fear-mongering, and white"
69
+ segment,3,63,aligned / aligned,,,,,,,0.0, supremacist conspiracy theories.
70
+ segment,3,64,aligned / aligned,,,,,,,0.0," ""They're teaching about Muhammad and Allah."
71
+ segment,3,65,aligned / aligned,,,,,,,0.0," We view more terror to children to be too about ABGTQ and what partners are belief, what they"
72
+ segment,3,66,aligned / aligned,,,,,,,0.0, can identify as.
73
+ segment,3,67,aligned / aligned,,,,,,,0.0," We view more terror to that one."""
74
+ segment,3,68,aligned / aligned,,,,,,,0.0," What they can identify as, we've been there to hate that round here."
75
+ window,4,,matched,0.45,0.832,0.000528,9e-06,1501,1501,,
76
+ segment,4,69,aligned / aligned,,,,,,,0.0, Keep up the pressure and one day you will be victorious!
77
+ segment,4,70,aligned / aligned,,,,,,,0.0," At this one tiny town's protest, we find one of the leaders of the UK's extreme right."
78
+ segment,4,71,aligned / aligned,,,,,,,0.0, I can't just be taken over by my immigration.
79
+ segment,4,72,aligned / aligned,,,,,,,0.0," We're fed up. This is not the future that our granddad, grandparents and great-grandparents"
80
+ segment,4,73,aligned / aligned,,,,,,,0.0, fought for in two world wars. Many fight for this to be done to our country.
81
+ segment,4,74,aligned / aligned,,,,,,,0.0, I live in these land and white groups.
82
+ segment,4,75,aligned / aligned,,,,,,,0.0, We want our country to be like it was before this immigration invasion was voiced in on us.
83
+ segment,4,76,aligned / aligned,,,,,,,0.0," Yes, you mentioned far right neo-narcia all that a minute ago."
84
+ segment,4,77,aligned / aligned,,,,,,,0.0, As if that kind of stuff doesn't hold any power anymore.
85
+ segment,4,78,aligned / aligned,,,,,,,0.0, You must have known this with Trump's victory.
86
+ segment,4,79,aligned / aligned,,,,,,,0.0, No one cares if they call it racist.
87
+ segment,4,80,aligned / aligned,,,,,,,0.0, Those terms are just used to silence people.
88
+ segment,4,81,aligned / aligned,,,,,,,0.0, The reelection of Donald Trump does not only mean inspiration for this one extreme right figure.
89
+ segment,4,82,aligned / aligned,,,,,,,0.0," At every far right event I've been to, it is a constant theme."
90
+ segment,4,83,aligned / aligned,,,,,,,0.0, Trump's Make America Great Again has come to the UK.
91
+ segment,4,84,aligned / aligned,,,,,,,0.0, has come to the UK.
92
+ window,5,,matched,0.446,0.835,0.000225,1.2e-05,1501,1501,,
93
+ segment,5,85,aligned / aligned,,,,,,,0.0," This is mega, make England great again."
94
+ segment,5,86,aligned / aligned,,,,,,,0.0, I have so much respect for President Trump.
95
+ segment,5,87,aligned / aligned,,,,,,,0.0," He is saving, not just America,"
96
+ segment,5,88,aligned / aligned,,,,,,,0.0, he is saving the West and in saving the world.
97
+ segment,5,89,aligned / aligned,,,,,,,0.0, You are wearing this because...
98
+ segment,5,90,aligned / aligned,,,,,,,0.0, Because I'm a Donald fan.
99
+ segment,5,91,aligned / aligned,,,,,,,0.0, What is it that's going on?
100
+ segment,5,92,aligned / aligned,,,,,,,0.0, How much of this is really influence from the US?
101
+ segment,5,93,aligned / aligned,,,,,,,0.0, There's no question there's a huge influence.
102
+ segment,5,94,aligned / aligned,,,,,,,0.0," When the far right is small little fringe political parties,"
103
+ segment,5,95,aligned / aligned,,,,,,,0.0, that sounds fanciful.
104
+ segment,5,96,aligned / aligned,,,,,,,0.0," When you've got Donald Trump in the White House,"
105
+ segment,5,97,aligned / aligned,,,,,,,0.0," the most powerful man in the world,"
106
+ segment,5,98,aligned / aligned,,,,,,,0.0," they can then point someone and say,"
107
+ segment,5,99,aligned / aligned,,,,,,,0.0," ""Look, it's happened there. If it can happen there, it can happen here."""
108
+ segment,5,100,aligned / aligned,,,,,,,0.0, Are we headed into a direction where the far right is turning
109
+ segment,5,101,aligned / aligned,,,,,,,0.0, into a significant political force in Britain?
110
+ segment,5,102,aligned / aligned,,,,,,,0.0," I think there's no doubt about it, right?"
111
+ segment,5,103,aligned / aligned,,,,,,,0.0, The far right is no longer something that sits on the very margins
112
+ segment,5,104,aligned / aligned,,,,,,,0.0, of our politics in Britain and annoyance to the right.
113
+ segment,5,105,aligned / aligned,,,,,,,0.0, It is increasingly something that actually has the real chance of taking the right.
114
+ segment,5,106,aligned / aligned,,,,,,,0.0, it is increasingly something that actually has the real chance of taking power in Britain.
115
+ window,6,,matched,0.127,0.147,0.000168,1.1e-05,396,396,,
116
+ segment,6,107,aligned / aligned,,,,,,,0.0, The once fringe voices seem to be moving into the mainstream.
117
+ segment,6,108,aligned / aligned,,,,,,,0.0, It's a small but vocal minority that's threatening to change the face of Britain.
118
+ segment,6,109,aligned / aligned,,,,,,,0.0, Now they believe their moment has arrived.
parity/parity_1gzKSyOBpZg.json ADDED
The diff for this file is too large to render. See raw diff
 
stt_en_conformer_ctc_small_features.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8998fd44bc2374c7d085f7c709fbfbd28ea6db09998622077071faf478db24fd
3
+ size 53197388
tokenizer/model_config.yaml ADDED
@@ -0,0 +1,1136 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ sample_rate: 16000
2
+ log_prediction: true
3
+ ctc_reduction: mean_batch
4
+ train_ds:
5
+ manifest_filepath: /data/NeMo_ASR_SET/English/v2.0/train/tarred_audio_manifest.json
6
+ sample_rate: 16000
7
+ batch_size: 64
8
+ shuffle: true
9
+ num_workers: 8
10
+ pin_memory: true
11
+ use_start_end_token: false
12
+ trim_silence: false
13
+ max_duration: 20.0
14
+ min_duration: 0.1
15
+ shuffle_n: 2048
16
+ is_tarred: true
17
+ tarred_audio_filepaths: /data/NeMo_ASR_SET/English/v2.0/train/audio__OP_0..4095_CL_.tar
18
+ validation_ds:
19
+ manifest_filepath:
20
+ - /data/ASR/LibriSpeech/librispeech_withsp2/manifests/librivox-dev-other.json
21
+ - /data/ASR/LibriSpeech/librispeech_withsp2/manifests/librivox-dev-clean.json
22
+ - /data/ASR/LibriSpeech/librispeech_withsp2/manifests/librivox-test-other.json
23
+ - /data/ASR/LibriSpeech/librispeech_withsp2/manifests/librivox-test-clean.json
24
+ sample_rate: 16000
25
+ batch_size: 64
26
+ shuffle: false
27
+ num_workers: 8
28
+ pin_memory: true
29
+ use_start_end_token: false
30
+ is_tarred: false
31
+ tarred_audio_filepaths: na
32
+ test_ds:
33
+ manifest_filepath:
34
+ - /data/ASR/LibriSpeech/librispeech_withsp2/manifests/librivox-test-other.json
35
+ - /data/ASR/LibriSpeech/librispeech_withsp2/manifests/librivox-dev-clean.json
36
+ - /data/ASR/LibriSpeech/librispeech_withsp2/manifests/librivox-dev-other.json
37
+ - /data/ASR/LibriSpeech/librispeech_withsp2/manifests/librivox-test-clean.json
38
+ sample_rate: 16000
39
+ batch_size: 64
40
+ shuffle: false
41
+ num_workers: 8
42
+ pin_memory: true
43
+ use_start_end_token: false
44
+ is_tarred: false
45
+ tarred_audio_filepaths: na
46
+ tokenizer:
47
+ dir: /tokenizers/NeMo_ASR_SET/English/asr_set_2.0/tokenizer_spe_unigram_v1024/
48
+ type: bpe
49
+ model_path: nemo:977d4e24975b431ebb44f2dfcdea8778_tokenizer.model
50
+ vocab_path: nemo:29fcf21b9e6e4fb5b1ba0bb1efd4197e_vocab.txt
51
+ spe_tokenizer_vocab: nemo:cf241f7e4d904eaea46bb96f21dd0b1d_tokenizer.vocab
52
+ preprocessor:
53
+ _target_: nemo.collections.asr.modules.AudioToMelSpectrogramPreprocessor
54
+ sample_rate: 16000
55
+ normalize: per_feature
56
+ window_size: 0.025
57
+ window_stride: 0.01
58
+ window: hann
59
+ features: 80
60
+ n_fft: 512
61
+ log: true
62
+ frame_splicing: 1
63
+ dither: 1.0e-05
64
+ pad_to: 0
65
+ pad_value: 0.0
66
+ spec_augment:
67
+ _target_: nemo.collections.asr.modules.SpectrogramAugmentation
68
+ freq_masks: 2
69
+ time_masks: 5
70
+ freq_width: 27
71
+ time_width: 0.05
72
+ encoder:
73
+ _target_: nemo.collections.asr.modules.ConformerEncoder
74
+ feat_in: 80
75
+ feat_out: -1
76
+ n_layers: 16
77
+ d_model: 176
78
+ subsampling: striding
79
+ subsampling_factor: 4
80
+ subsampling_conv_channels: 176
81
+ ff_expansion_factor: 4
82
+ self_attention_model: rel_pos
83
+ n_heads: 4
84
+ att_context_size:
85
+ - -1
86
+ - -1
87
+ xscaling: true
88
+ untie_biases: true
89
+ pos_emb_max_len: 5000
90
+ conv_kernel_size: 31
91
+ dropout: 0.1
92
+ dropout_emb: 0.0
93
+ dropout_att: 0.1
94
+ decoder:
95
+ _target_: nemo.collections.asr.modules.ConvASRDecoder
96
+ feat_in: 176
97
+ num_classes: 1024
98
+ vocabulary:
99
+ - <unk>
100
+ - s
101
+ - ▁the
102
+ - ▁a
103
+ - t
104
+ - ▁to
105
+ - ▁and
106
+ - ▁i
107
+ - ▁of
108
+ - ''''
109
+ - ed
110
+ - ▁in
111
+ - d
112
+ - ing
113
+ - 'n'
114
+ - e
115
+ - ▁it
116
+ - ▁that
117
+ - ▁you
118
+ - 'y'
119
+ - er
120
+ - r
121
+ - ▁for
122
+ - m
123
+ - ▁is
124
+ - ▁he
125
+ - re
126
+ - ▁was
127
+ - ▁be
128
+ - p
129
+ - ly
130
+ - ▁so
131
+ - ▁we
132
+ - a
133
+ - g
134
+ - o
135
+ - ▁c
136
+ - b
137
+ - u
138
+ - ▁on
139
+ - ▁have
140
+ - ▁but
141
+ - ll
142
+ - ▁with
143
+ - ▁re
144
+ - or
145
+ - ▁s
146
+ - al
147
+ - ▁do
148
+ - ▁know
149
+ - ar
150
+ - ▁they
151
+ - ▁not
152
+ - ▁as
153
+ - ▁this
154
+ - in
155
+ - le
156
+ - ▁e
157
+ - ▁are
158
+ - ▁like
159
+ - c
160
+ - ▁uh
161
+ - ri
162
+ - ▁me
163
+ - ▁his
164
+ - ▁at
165
+ - l
166
+ - es
167
+ - ▁de
168
+ - ▁yeah
169
+ - ▁can
170
+ - k
171
+ - ▁or
172
+ - ▁my
173
+ - ▁all
174
+ - ▁had
175
+ - ▁there
176
+ - ▁will
177
+ - ▁one
178
+ - il
179
+ - ▁no
180
+ - ▁what
181
+ - en
182
+ - ck
183
+ - ▁b
184
+ - ▁f
185
+ - ce
186
+ - ch
187
+ - i
188
+ - ▁by
189
+ - ▁she
190
+ - ▁from
191
+ - ▁an
192
+ - ic
193
+ - ur
194
+ - ve
195
+ - w
196
+ - ter
197
+ - la
198
+ - ▁if
199
+ - ▁just
200
+ - th
201
+ - li
202
+ - ▁
203
+ - ▁her
204
+ - ▁um
205
+ - 'on'
206
+ - ation
207
+ - ▁w
208
+ - ▁would
209
+ - f
210
+ - te
211
+ - ▁st
212
+ - ▁go
213
+ - ir
214
+ - it
215
+ - ▁out
216
+ - ro
217
+ - ▁pa
218
+ - ▁were
219
+ - ▁g
220
+ - ▁t
221
+ - ion
222
+ - ▁think
223
+ - an
224
+ - ▁right
225
+ - ▁about
226
+ - se
227
+ - lo
228
+ - ent
229
+ - ▁up
230
+ - ment
231
+ - ate
232
+ - ▁when
233
+ - h
234
+ - ne
235
+ - ▁don
236
+ - ▁has
237
+ - ▁also
238
+ - ▁more
239
+ - ▁see
240
+ - ▁okay
241
+ - ▁their
242
+ - ▁your
243
+ - ge
244
+ - ▁who
245
+ - ▁well
246
+ - ▁co
247
+ - ▁which
248
+ - ▁some
249
+ - ▁se
250
+ - ▁time
251
+ - ▁ba
252
+ - ▁said
253
+ - ▁con
254
+ - ers
255
+ - ▁ra
256
+ - us
257
+ - de
258
+ - ra
259
+ - ▁him
260
+ - ▁our
261
+ - ▁been
262
+ - ▁fa
263
+ - ▁po
264
+ - ▁pro
265
+ - et
266
+ - x
267
+ - ▁la
268
+ - id
269
+ - ver
270
+ - ▁oh
271
+ - ▁ma
272
+ - v
273
+ - ▁now
274
+ - age
275
+ - ▁two
276
+ - ld
277
+ - ▁mo
278
+ - ▁how
279
+ - tion
280
+ - ▁people
281
+ - ive
282
+ - ▁other
283
+ - ng
284
+ - ity
285
+ - z
286
+ - ist
287
+ - ▁very
288
+ - ▁get
289
+ - ▁any
290
+ - ▁un
291
+ - ▁ro
292
+ - is
293
+ - ▁work
294
+ - ▁mean
295
+ - ▁them
296
+ - ▁lo
297
+ - vi
298
+ - ▁because
299
+ - ies
300
+ - ul
301
+ - as
302
+ - ad
303
+ - mp
304
+ - ▁bo
305
+ - '-'
306
+ - ▁then
307
+ - ▁good
308
+ - el
309
+ - nd
310
+ - ▁li
311
+ - ▁man
312
+ - ▁dis
313
+ - ▁could
314
+ - ▁ho
315
+ - at
316
+ - ol
317
+ - ▁bu
318
+ - ▁te
319
+ - ▁ha
320
+ - est
321
+ - me
322
+ - ▁say
323
+ - ru
324
+ - ke
325
+ - ▁sp
326
+ - ▁k
327
+ - able
328
+ - ▁su
329
+ - ▁sa
330
+ - ▁di
331
+ - ▁fi
332
+ - ance
333
+ - ▁really
334
+ - ▁over
335
+ - ▁even
336
+ - ry
337
+ - ▁us
338
+ - ▁ca
339
+ - ow
340
+ - ho
341
+ - ▁into
342
+ - ence
343
+ - mo
344
+ - ▁mi
345
+ - one
346
+ - qu
347
+ - ut
348
+ - lu
349
+ - ▁o
350
+ - ty
351
+ - ▁after
352
+ - ▁want
353
+ - ▁new
354
+ - ▁take
355
+ - ▁p
356
+ - ▁look
357
+ - ▁pre
358
+ - sh
359
+ - ▁day
360
+ - ▁should
361
+ - ▁th
362
+ - ▁need
363
+ - ▁cha
364
+ - co
365
+ - ▁much
366
+ - ▁where
367
+ - ▁d
368
+ - ant
369
+ - ▁fe
370
+ - ▁da
371
+ - ▁make
372
+ - om
373
+ - ▁did
374
+ - ▁le
375
+ - un
376
+ - ▁only
377
+ - im
378
+ - ▁these
379
+ - ff
380
+ - ti
381
+ - ish
382
+ - ▁ex
383
+ - ted
384
+ - ▁first
385
+ - he
386
+ - ig
387
+ - ▁vi
388
+ - ▁ri
389
+ - ▁en
390
+ - ▁com
391
+ - ated
392
+ - ▁than
393
+ - ma
394
+ - ▁way
395
+ - um
396
+ - ct
397
+ - end
398
+ - ight
399
+ - ▁here
400
+ - ▁ta
401
+ - ▁car
402
+ - ▁part
403
+ - ▁come
404
+ - ia
405
+ - ▁off
406
+ - ▁sc
407
+ - ▁ah
408
+ - am
409
+ - ▁tra
410
+ - ▁yes
411
+ - ▁back
412
+ - ture
413
+ - ful
414
+ - ▁pri
415
+ - ction
416
+ - ine
417
+ - ▁three
418
+ - ard
419
+ - ▁let
420
+ - pe
421
+ - ▁little
422
+ - ▁down
423
+ - mb
424
+ - ▁si
425
+ - ▁dr
426
+ - ▁mr
427
+ - ▁going
428
+ - ▁comp
429
+ - po
430
+ - ▁m
431
+ - ▁sta
432
+ - ▁gra
433
+ - day
434
+ - ▁many
435
+ - ian
436
+ - ta
437
+ - ▁long
438
+ - ▁pi
439
+ - ▁too
440
+ - ▁app
441
+ - ▁kind
442
+ - ous
443
+ - ci
444
+ - ▁ga
445
+ - ten
446
+ - nt
447
+ - ▁before
448
+ - ▁may
449
+ - ▁got
450
+ - man
451
+ - tic
452
+ - ition
453
+ - cu
454
+ - ugh
455
+ - tra
456
+ - ▁n
457
+ - ward
458
+ - ▁give
459
+ - ▁every
460
+ - ▁hi
461
+ - ting
462
+ - ▁exp
463
+ - ▁those
464
+ - ▁hu
465
+ - ot
466
+ - ▁something
467
+ - ▁lot
468
+ - ▁still
469
+ - ▁ne
470
+ - na
471
+ - ise
472
+ - pp
473
+ - ▁most
474
+ - ▁gu
475
+ - ▁state
476
+ - ▁actually
477
+ - ▁such
478
+ - ▁bi
479
+ - ▁never
480
+ - tain
481
+ - ▁great
482
+ - ▁through
483
+ - ▁al
484
+ - 'no'
485
+ - ▁mar
486
+ - ▁year
487
+ - ach
488
+ - les
489
+ - ▁school
490
+ - ally
491
+ - ial
492
+ - ha
493
+ - ▁old
494
+ - ▁made
495
+ - ary
496
+ - ▁ar
497
+ - ▁years
498
+ - ▁help
499
+ - ▁per
500
+ - ving
501
+ - ical
502
+ - ther
503
+ - ▁does
504
+ - ac
505
+ - ca
506
+ - ▁must
507
+ - di
508
+ - ▁own
509
+ - ▁ru
510
+ - ▁things
511
+ - ▁hand
512
+ - ▁thing
513
+ - ▁high
514
+ - ▁last
515
+ - go
516
+ - ▁sh
517
+ - ▁under
518
+ - ▁four
519
+ - ▁place
520
+ - ations
521
+ - ▁sure
522
+ - mi
523
+ - nce
524
+ - ▁am
525
+ - for
526
+ - ness
527
+ - ▁name
528
+ - ▁five
529
+ - ound
530
+ - ▁op
531
+ - ▁cons
532
+ - ▁ph
533
+ - ▁same
534
+ - row
535
+ - ven
536
+ - ph
537
+ - ite
538
+ - ▁pe
539
+ - j
540
+ - ▁sha
541
+ - ▁friend
542
+ - ▁wi
543
+ - ▁call
544
+ - ▁european
545
+ - ▁h
546
+ - ect
547
+ - ress
548
+ - ▁live
549
+ - port
550
+ - ▁mhm
551
+ - ▁house
552
+ - ie
553
+ - ni
554
+ - ▁plan
555
+ - ▁jo
556
+ - ▁play
557
+ - side
558
+ - ▁va
559
+ - min
560
+ - ious
561
+ - ▁life
562
+ - ▁du
563
+ - ▁ti
564
+ - ▁six
565
+ - ▁men
566
+ - ▁again
567
+ - ▁thank
568
+ - ▁talk
569
+ - par
570
+ - ▁home
571
+ - op
572
+ - ▁both
573
+ - ▁why
574
+ - ▁put
575
+ - ▁another
576
+ - nc
577
+ - ▁being
578
+ - mit
579
+ - ▁came
580
+ - led
581
+ - ▁fo
582
+ - ▁end
583
+ - ▁member
584
+ - ative
585
+ - ▁thought
586
+ - ▁tri
587
+ - iv
588
+ - our
589
+ - red
590
+ - ▁went
591
+ - lic
592
+ - ▁find
593
+ - ▁pu
594
+ - land
595
+ - ▁start
596
+ - ▁far
597
+ - ▁eu
598
+ - ▁imp
599
+ - ▁always
600
+ - ▁ju
601
+ - ▁wa
602
+ - ▁person
603
+ - ▁singapore
604
+ - ap
605
+ - ▁show
606
+ - ▁chi
607
+ - ▁ten
608
+ - ▁eight
609
+ - ▁while
610
+ - ▁point
611
+ - ▁y
612
+ - ▁ja
613
+ - ▁ya
614
+ - ling
615
+ - ctor
616
+ - ▁use
617
+ - ▁acc
618
+ - ▁world
619
+ - ▁pay
620
+ - ▁read
621
+ - va
622
+ - vo
623
+ - ▁change
624
+ - ▁u
625
+ - ▁pl
626
+ - ▁sw
627
+ - ▁war
628
+ - ▁might
629
+ - nk
630
+ - ments
631
+ - and
632
+ - ▁different
633
+ - ▁dec
634
+ - cent
635
+ - ▁ste
636
+ - ▁better
637
+ - ▁fun
638
+ - ▁month
639
+ - ship
640
+ - ton
641
+ - ▁tell
642
+ - ▁twenty
643
+ - ▁commission
644
+ - ▁exc
645
+ - ▁miss
646
+ - if
647
+ - ▁love
648
+ - ▁money
649
+ - ▁found
650
+ - ▁hundred
651
+ - gg
652
+ - ▁add
653
+ - ▁real
654
+ - ities
655
+ - ▁na
656
+ - ▁pass
657
+ - ▁didn
658
+ - ▁v
659
+ - ▁feel
660
+ - ▁week
661
+ - ▁win
662
+ - ible
663
+ - ▁try
664
+ - ▁upon
665
+ - ba
666
+ - ▁interest
667
+ - ▁inter
668
+ - son
669
+ - line
670
+ - ▁ob
671
+ - ▁boy
672
+ - ▁big
673
+ - ▁used
674
+ - ▁seven
675
+ - ▁away
676
+ - ▁family
677
+ - less
678
+ - ▁ki
679
+ - ber
680
+ - ▁around
681
+ - ▁turn
682
+ - ▁anything
683
+ - ▁care
684
+ - ▁young
685
+ - ▁guess
686
+ - ▁happen
687
+ - ▁course
688
+ - ▁agree
689
+ - ▁support
690
+ - ▁conf
691
+ - ual
692
+ - ▁number
693
+ - ▁trans
694
+ - ating
695
+ - ▁mister
696
+ - ▁hard
697
+ - ▁watch
698
+ - ft
699
+ - ▁next
700
+ - ▁sea
701
+ - ▁open
702
+ - ▁without
703
+ - duc
704
+ - gra
705
+ - ak
706
+ - ▁cap
707
+ - ▁cre
708
+ - hi
709
+ - ▁government
710
+ - ▁vo
711
+ - ▁between
712
+ - ▁each
713
+ - ▁ve
714
+ - ▁though
715
+ - ▁country
716
+ - ▁few
717
+ - ▁once
718
+ - ▁'
719
+ - ▁head
720
+ - ▁free
721
+ - ▁mu
722
+ - ▁maybe
723
+ - ▁act
724
+ - ▁night
725
+ - ▁thousand
726
+ - ▁face
727
+ - ▁uhhuh
728
+ - ▁keep
729
+ - ▁nine
730
+ - ▁close
731
+ - ▁case
732
+ - ▁che
733
+ - ▁against
734
+ - ▁done
735
+ - ▁ever
736
+ - ▁law
737
+ - ▁believe
738
+ - ▁public
739
+ - ▁room
740
+ - ▁sub
741
+ - ▁order
742
+ - ▁important
743
+ - ient
744
+ - ▁el
745
+ - ▁children
746
+ - ▁second
747
+ - ▁bri
748
+ - ▁business
749
+ - ▁hope
750
+ - ▁move
751
+ - fa
752
+ - ▁however
753
+ - ▁follow
754
+ - ▁able
755
+ - ▁word
756
+ - ▁yet
757
+ - ▁fla
758
+ - ▁stand
759
+ - ize
760
+ - ▁je
761
+ - ▁service
762
+ - ▁nothing
763
+ - ▁report
764
+ - ▁called
765
+ - ▁grow
766
+ - ▁continue
767
+ - ▁issue
768
+ - ▁since
769
+ - ▁book
770
+ - ▁lu
771
+ - ▁qui
772
+ - ▁develop
773
+ - ▁gen
774
+ - ▁certain
775
+ - light
776
+ - ▁cor
777
+ - ▁small
778
+ - ▁took
779
+ - ▁question
780
+ - ▁whole
781
+ - ▁problem
782
+ - ▁side
783
+ - ▁child
784
+ - ▁full
785
+ - ▁best
786
+ - ▁mm
787
+ - ▁probably
788
+ - fi
789
+ - ▁qua
790
+ - ▁sur
791
+ - ▁market
792
+ - ▁left
793
+ - ▁everything
794
+ - ▁during
795
+ - ▁understand
796
+ - ook
797
+ - wa
798
+ - ▁cent
799
+ - ▁water
800
+ - ▁quite
801
+ - ▁leave
802
+ - ▁himself
803
+ - ip
804
+ - ▁near
805
+ - ▁saw
806
+ - ▁together
807
+ - ▁large
808
+ - ▁having
809
+ - ▁already
810
+ - ▁invest
811
+ - ▁pretty
812
+ - ▁direct
813
+ - ▁hour
814
+ - ▁fact
815
+ - way
816
+ - ▁run
817
+ - ▁bra
818
+ - ▁clear
819
+ - ▁fra
820
+ - ▁area
821
+ - ▁union
822
+ - ▁enough
823
+ - ▁consider
824
+ - ▁lead
825
+ - ▁remain
826
+ - ▁president
827
+ - ▁system
828
+ - ▁def
829
+ - ▁stuff
830
+ - ▁food
831
+ - ▁job
832
+ - ▁heard
833
+ - ▁err
834
+ - ▁mind
835
+ - ▁rest
836
+ - ▁speak
837
+ - ▁asked
838
+ - ator
839
+ - ▁half
840
+ - ▁father
841
+ - com
842
+ - ▁less
843
+ - ▁arm
844
+ - ▁human
845
+ - ency
846
+ - ▁matter
847
+ - ▁group
848
+ - ▁girl
849
+ - ▁current
850
+ - ▁main
851
+ - ttle
852
+ - ▁later
853
+ - ▁learn
854
+ - ▁strong
855
+ - ▁sign
856
+ - ▁check
857
+ - ▁light
858
+ - ▁else
859
+ - ▁true
860
+ - ▁term
861
+ - qui
862
+ - ▁minute
863
+ - ▁spec
864
+ - ▁return
865
+ - ▁answer
866
+ - ▁reason
867
+ - ▁count
868
+ - ▁shall
869
+ - ▁communi
870
+ - ▁travel
871
+ - ▁wait
872
+ - ▁provide
873
+ - ▁low
874
+ - ▁mother
875
+ - ▁expect
876
+ - ▁cause
877
+ - ▁line
878
+ - ▁general
879
+ - lf
880
+ - ▁getting
881
+ - ▁parliament
882
+ - ▁bank
883
+ - ▁company
884
+ - ▁stop
885
+ - cause
886
+ - ▁power
887
+ - ▁gi
888
+ - ▁europe
889
+ - ▁moment
890
+ - ▁among
891
+ - ▁walk
892
+ - ▁allow
893
+ - ▁idea
894
+ - ▁office
895
+ - ▁town
896
+ - ▁cannot
897
+ - ▁countries
898
+ - ▁become
899
+ - ▁appear
900
+ - ▁present
901
+ - ▁bring
902
+ - ▁least
903
+ - ▁almost
904
+ - ▁kids
905
+ - ▁remember
906
+ - ▁include
907
+ - ▁short
908
+ - ▁sometimes
909
+ - ▁game
910
+ - ▁level
911
+ - ▁exactly
912
+ - ▁particular
913
+ - ▁social
914
+ - ▁land
915
+ - ▁woman
916
+ - ▁north
917
+ - ▁nice
918
+ - ▁concern
919
+ - ▁sort
920
+ - ▁effect
921
+ - ▁national
922
+ - ▁several
923
+ - ▁safe
924
+ - ▁until
925
+ - ▁further
926
+ - ▁cost
927
+ - ▁wonder
928
+ - ▁whether
929
+ - ▁either
930
+ - ▁future
931
+ - ▁pra
932
+ - ▁council
933
+ - ▁knew
934
+ - ▁common
935
+ - ▁south
936
+ - ▁making
937
+ - ▁morning
938
+ - ▁process
939
+ - ▁situation
940
+ - ▁white
941
+ - ▁result
942
+ - ▁suppose
943
+ - ▁employ
944
+ - ▁political
945
+ - ▁program
946
+ - ▁along
947
+ - ▁women
948
+ - ▁ski
949
+ - ▁court
950
+ - ▁please
951
+ - ▁shi
952
+ - ▁possible
953
+ - ▁protect
954
+ - ▁experience
955
+ - ▁definitely
956
+ - ▁require
957
+ - ▁account
958
+ - ▁myself
959
+ - ▁black
960
+ - ▁example
961
+ - ▁america
962
+ - ▁thirty
963
+ - ▁student
964
+ - ▁view
965
+ - ▁product
966
+ - ▁wife
967
+ - ▁health
968
+ - ▁major
969
+ - ▁difficult
970
+ - ▁death
971
+ - ▁visit
972
+ - ▁across
973
+ - ▁receive
974
+ - ▁voice
975
+ - ▁citizen
976
+ - ▁regard
977
+ - ▁author
978
+ - ▁treat
979
+ - ▁especially
980
+ - ▁local
981
+ - ▁taking
982
+ - ▁information
983
+ - ▁seemed
984
+ - ▁success
985
+ - ability
986
+ - ▁break
987
+ - ▁whatever
988
+ - ▁security
989
+ - ▁address
990
+ - ▁felt
991
+ - ▁fifty
992
+ - ▁million
993
+ - ▁third
994
+ - ▁usually
995
+ - ▁gonna
996
+ - ▁brother
997
+ - ▁began
998
+ - ▁period
999
+ - ▁east
1000
+ - ▁economic
1001
+ - ▁increase
1002
+ - ▁financial
1003
+ - ▁respect
1004
+ - ▁enjoy
1005
+ - ▁christ
1006
+ - ▁education
1007
+ - ▁brought
1008
+ - ▁organ
1009
+ - ▁parents
1010
+ - ▁policy
1011
+ - ▁round
1012
+ - ▁became
1013
+ - ▁region
1014
+ - ▁lady
1015
+ - ▁discuss
1016
+ - ▁single
1017
+ - ▁early
1018
+ - ▁couple
1019
+ - ▁type
1020
+ - ▁itself
1021
+ - ▁serve
1022
+ - ▁measure
1023
+ - ▁husband
1024
+ - ified
1025
+ - ▁music
1026
+ - ▁ground
1027
+ - ▁companies
1028
+ - ▁street
1029
+ - ▁behind
1030
+ - ▁value
1031
+ - ▁therefore
1032
+ - ▁police
1033
+ - ▁complete
1034
+ - ▁john
1035
+ - ▁daughter
1036
+ - ▁affect
1037
+ - ▁perhaps
1038
+ - ▁international
1039
+ - ▁themselves
1040
+ - ▁improve
1041
+ - ▁condition
1042
+ - ▁hotel
1043
+ - ▁deliver
1044
+ - ▁sense
1045
+ - ▁relation
1046
+ - ▁sorry
1047
+ - ▁credit
1048
+ - ▁effort
1049
+ - ▁instead
1050
+ - ▁york
1051
+ - ▁united
1052
+ - ▁partner
1053
+ - ▁spoke
1054
+ - ▁strange
1055
+ - ▁everybody
1056
+ - ▁horse
1057
+ - ▁depend
1058
+ - ▁subject
1059
+ - ▁project
1060
+ - ▁approach
1061
+ - ▁involve
1062
+ - ▁listen
1063
+ - ▁draw
1064
+ - ▁computer
1065
+ - ▁married
1066
+ - ▁record
1067
+ - ▁happy
1068
+ - ▁sudden
1069
+ - ▁represent
1070
+ - ▁somebody
1071
+ - ▁correct
1072
+ - ▁serious
1073
+ - ▁decision
1074
+ - ▁society
1075
+ - ▁including
1076
+ - ▁college
1077
+ - ▁english
1078
+ - ▁attack
1079
+ - ▁perform
1080
+ - ▁cross
1081
+ - ▁accept
1082
+ - ▁control
1083
+ - ▁flow
1084
+ - ▁although
1085
+ - ▁drink
1086
+ - ▁front
1087
+ - ▁wrong
1088
+ - ▁twi
1089
+ - ▁according
1090
+ - ▁slow
1091
+ - ▁peace
1092
+ - ▁amount
1093
+ - ▁object
1094
+ - ▁movie
1095
+ - ▁benefit
1096
+ - ▁yup
1097
+ - ▁challenge
1098
+ - ▁private
1099
+ - ▁church
1100
+ - ▁wood
1101
+ - ▁field
1102
+ - ▁above
1103
+ - ▁ensure
1104
+ - ▁immediate
1105
+ - ▁figure
1106
+ - ▁foreign
1107
+ - ▁available
1108
+ - ▁insurance
1109
+ - ▁proposal
1110
+ - ▁doubt
1111
+ - ▁strength
1112
+ - ▁difference
1113
+ - ▁stood
1114
+ - ▁implement
1115
+ - ▁economy
1116
+ - ▁detail
1117
+ - ▁umhum
1118
+ - ▁restaurant
1119
+ - ▁collect
1120
+ - ▁global
1121
+ - ▁broke
1122
+ - q
1123
+ optim:
1124
+ name: adamw
1125
+ lr: 2.0
1126
+ betas:
1127
+ - 0.9
1128
+ - 0.98
1129
+ weight_decay: 0
1130
+ sched:
1131
+ name: NoamAnnealing
1132
+ d_model: 176
1133
+ warmup_steps: 10000
1134
+ warmup_ratio: null
1135
+ min_lr: 1.0e-06
1136
+ target: nemo.collections.asr.models.ctc_bpe_models.EncDecCTCModelBPE
tokenizer/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9b04033136c5d0413047fe94d2f0ab6cb088d292014bb076ee1700bdac545a9
3
+ size 260411
tokenizer/tokenizer.vocab ADDED
@@ -0,0 +1,1024 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <unk> 0
2
+ s -3.0263
3
+ ▁the -3.41766
4
+ ▁a -3.9762
5
+ t -4.01176
6
+ ▁to -4.02202
7
+ ▁and -4.04939
8
+ ▁i -4.14288
9
+ ▁of -4.25654
10
+ ' -4.32966
11
+ ed -4.41167
12
+ ▁in -4.45237
13
+ d -4.45877
14
+ ing -4.53241
15
+ n -4.56881
16
+ e -4.62574
17
+ ▁it -4.65761
18
+ ▁that -4.66105
19
+ ▁you -4.66842
20
+ y -4.80029
21
+ er -4.92503
22
+ r -4.94797
23
+ ▁for -5.00422
24
+ m -5.00985
25
+ ▁is -5.04904
26
+ ▁he -5.13475
27
+ re -5.21796
28
+ ▁was -5.22137
29
+ ▁be -5.25517
30
+ p -5.27288
31
+ ly -5.28375
32
+ ▁so -5.31924
33
+ ▁we -5.36619
34
+ a -5.41184
35
+ g -5.43206
36
+ o -5.43275
37
+ ▁c -5.44933
38
+ b -5.47847
39
+ u -5.49905
40
+ ▁on -5.50807
41
+ ▁have -5.5109
42
+ ▁but -5.51464
43
+ ll -5.51628
44
+ ▁with -5.51689
45
+ ▁re -5.54855
46
+ or -5.5861
47
+ ▁s -5.58872
48
+ al -5.60085
49
+ ▁do -5.61746
50
+ ▁know -5.62175
51
+ ar -5.64978
52
+ ▁they -5.65081
53
+ ▁not -5.65161
54
+ ▁as -5.66379
55
+ ▁this -5.68369
56
+ in -5.69316
57
+ le -5.70926
58
+ ▁e -5.71441
59
+ ▁are -5.73661
60
+ ▁like -5.77899
61
+ c -5.81055
62
+ ▁uh -5.86416
63
+ ri -5.86672
64
+ ▁me -5.87717
65
+ ▁his -5.88288
66
+ ▁at -5.88837
67
+ l -5.99474
68
+ es -6.00344
69
+ ▁de -6.00677
70
+ ▁yeah -6.02199
71
+ ▁can -6.05347
72
+ k -6.06257
73
+ ▁or -6.06696
74
+ ▁my -6.06989
75
+ ▁all -6.07977
76
+ ▁had -6.0971
77
+ ▁there -6.10531
78
+ ▁will -6.10972
79
+ ▁one -6.11344
80
+ il -6.11446
81
+ ▁no -6.12262
82
+ ▁what -6.12458
83
+ en -6.13206
84
+ ck -6.13865
85
+ ▁b -6.14598
86
+ ▁f -6.1574
87
+ ce -6.17153
88
+ ch -6.17679
89
+ i -6.18348
90
+ ▁by -6.18665
91
+ ▁she -6.19154
92
+ ▁from -6.19541
93
+ ▁an -6.19568
94
+ ic -6.20819
95
+ ur -6.20979
96
+ ve -6.22601
97
+ w -6.23968
98
+ ter -6.24495
99
+ la -6.2526
100
+ ▁if -6.25995
101
+ ▁just -6.2716
102
+ th -6.27748
103
+ li -6.28385
104
+ ▁ -6.2845
105
+ ▁her -6.28703
106
+ ▁um -6.29534
107
+ on -6.31318
108
+ ation -6.31753
109
+ ▁w -6.32975
110
+ ▁would -6.33558
111
+ f -6.33633
112
+ te -6.36164
113
+ ▁st -6.37187
114
+ ▁go -6.38758
115
+ ir -6.40928
116
+ it -6.41129
117
+ ▁out -6.41964
118
+ ro -6.42389
119
+ ▁pa -6.42399
120
+ ▁were -6.43243
121
+ ▁g -6.43733
122
+ ▁t -6.43754
123
+ ion -6.44863
124
+ ▁think -6.45619
125
+ an -6.4642
126
+ ▁right -6.46855
127
+ ▁about -6.4767
128
+ se -6.48153
129
+ lo -6.48217
130
+ ent -6.48888
131
+ ▁up -6.49777
132
+ ment -6.49927
133
+ ate -6.52341
134
+ ▁when -6.53144
135
+ h -6.53238
136
+ ne -6.53604
137
+ ▁don -6.53936
138
+ ▁has -6.55882
139
+ ▁also -6.56619
140
+ ▁more -6.56684
141
+ ▁see -6.5687
142
+ ▁okay -6.57173
143
+ ▁their -6.57539
144
+ ▁your -6.57664
145
+ ge -6.60217
146
+ ▁who -6.60997
147
+ ▁well -6.61219
148
+ ▁co -6.61255
149
+ ▁which -6.61274
150
+ ▁some -6.61714
151
+ ▁se -6.61804
152
+ ▁time -6.62142
153
+ ▁ba -6.62355
154
+ ▁said -6.63244
155
+ ▁con -6.64083
156
+ ers -6.64156
157
+ ▁ra -6.65025
158
+ us -6.65176
159
+ de -6.66205
160
+ ra -6.66792
161
+ ▁him -6.68277
162
+ ▁our -6.68791
163
+ ▁been -6.69063
164
+ ▁fa -6.69408
165
+ ▁po -6.70744
166
+ ▁pro -6.71192
167
+ et -6.71725
168
+ x -6.71916
169
+ ▁la -6.73553
170
+ id -6.74282
171
+ ver -6.74689
172
+ ▁oh -6.74706
173
+ ▁ma -6.75825
174
+ v -6.76115
175
+ ▁now -6.76235
176
+ age -6.76427
177
+ ▁two -6.76715
178
+ ld -6.76771
179
+ ▁mo -6.76887
180
+ ▁how -6.77155
181
+ tion -6.7937
182
+ ▁people -6.79744
183
+ ive -6.80143
184
+ ▁other -6.80534
185
+ ng -6.80715
186
+ ity -6.81352
187
+ z -6.81663
188
+ ist -6.83718
189
+ ▁very -6.84516
190
+ ▁get -6.85506
191
+ ▁any -6.86148
192
+ ▁un -6.86614
193
+ ▁ro -6.86987
194
+ is -6.87234
195
+ ▁work -6.88255
196
+ ▁mean -6.88295
197
+ ▁them -6.88553
198
+ ▁lo -6.88958
199
+ vi -6.89581
200
+ ▁because -6.89751
201
+ ies -6.89879
202
+ ul -6.90015
203
+ as -6.90824
204
+ ad -6.91023
205
+ mp -6.91547
206
+ ▁bo -6.9169
207
+ - -6.91865
208
+ ▁then -6.91935
209
+ ▁good -6.92813
210
+ el -6.93225
211
+ nd -6.93325
212
+ ▁li -6.936
213
+ ▁man -6.93624
214
+ ▁dis -6.94602
215
+ ▁could -6.95497
216
+ ▁ho -6.96697
217
+ at -6.96766
218
+ ol -6.97041
219
+ ▁bu -6.97092
220
+ ▁te -6.97702
221
+ ▁ha -6.98348
222
+ est -6.98549
223
+ me -6.99011
224
+ ▁say -6.99224
225
+ ru -6.99512
226
+ ke -6.99659
227
+ ▁sp -7.00212
228
+ ▁k -7.01427
229
+ able -7.01431
230
+ ▁su -7.01529
231
+ ▁sa -7.02578
232
+ ▁di -7.02821
233
+ ▁fi -7.03155
234
+ ance -7.03657
235
+ ▁really -7.03735
236
+ ▁over -7.03941
237
+ ▁even -7.05293
238
+ ry -7.05582
239
+ ▁us -7.05738
240
+ ▁ca -7.06337
241
+ ow -7.06468
242
+ ho -7.07761
243
+ ▁into -7.07966
244
+ ence -7.08333
245
+ mo -7.08787
246
+ ▁mi -7.08789
247
+ one -7.08829
248
+ qu -7.09051
249
+ ut -7.09374
250
+ lu -7.09945
251
+ ▁o -7.10004
252
+ ty -7.10264
253
+ ▁after -7.10287
254
+ ▁want -7.10504
255
+ ▁new -7.10788
256
+ ▁take -7.11305
257
+ ▁p -7.12212
258
+ ▁look -7.1312
259
+ ▁pre -7.13218
260
+ sh -7.13355
261
+ ▁day -7.14166
262
+ ▁should -7.14538
263
+ ▁th -7.15043
264
+ ▁need -7.15097
265
+ ▁cha -7.15336
266
+ co -7.15733
267
+ ▁much -7.16213
268
+ ▁where -7.16628
269
+ ▁d -7.16716
270
+ ant -7.16962
271
+ ▁fe -7.1718
272
+ ▁da -7.17488
273
+ ▁make -7.18448
274
+ om -7.18916
275
+ ▁did -7.19359
276
+ ▁le -7.19823
277
+ un -7.19886
278
+ ▁only -7.20642
279
+ im -7.20754
280
+ ▁these -7.20762
281
+ ff -7.20976
282
+ ti -7.21232
283
+ ish -7.21261
284
+ ▁ex -7.21338
285
+ ted -7.21551
286
+ ▁first -7.23735
287
+ he -7.24304
288
+ ig -7.24652
289
+ ▁vi -7.25989
290
+ ▁ri -7.26283
291
+ ▁en -7.27274
292
+ ▁com -7.27526
293
+ ated -7.27628
294
+ ▁than -7.28094
295
+ ma -7.28164
296
+ ▁way -7.28836
297
+ um -7.29041
298
+ ct -7.29154
299
+ end -7.29294
300
+ ight -7.29556
301
+ ▁here -7.31492
302
+ ▁ta -7.3183
303
+ ▁car -7.32546
304
+ ▁part -7.32842
305
+ ▁come -7.3299
306
+ ia -7.33231
307
+ ▁off -7.33717
308
+ ▁sc -7.33728
309
+ ▁ah -7.34222
310
+ am -7.34737
311
+ ▁tra -7.34964
312
+ ▁yes -7.35933
313
+ ▁back -7.35995
314
+ ture -7.3603
315
+ ful -7.36402
316
+ ▁pri -7.37566
317
+ ction -7.37631
318
+ ine -7.38027
319
+ ▁three -7.38034
320
+ ard -7.38252
321
+ ▁let -7.38935
322
+ pe -7.3907
323
+ ▁little -7.39645
324
+ ▁down -7.40305
325
+ mb -7.40994
326
+ ▁si -7.41456
327
+ ▁dr -7.41553
328
+ ▁mr -7.41781
329
+ ▁going -7.4185
330
+ ▁comp -7.42245
331
+ po -7.43274
332
+ ▁m -7.43719
333
+ ▁sta -7.43858
334
+ ▁gra -7.44028
335
+ day -7.44115
336
+ ▁many -7.44476
337
+ ian -7.44484
338
+ ta -7.44597
339
+ ▁long -7.44993
340
+ ▁pi -7.45578
341
+ ▁too -7.45677
342
+ ▁app -7.46234
343
+ ▁kind -7.46504
344
+ ous -7.46577
345
+ ci -7.47054
346
+ ▁ga -7.47277
347
+ ten -7.47296
348
+ nt -7.47766
349
+ ▁before -7.48153
350
+ ▁may -7.48629
351
+ ▁got -7.48682
352
+ man -7.48816
353
+ tic -7.49072
354
+ ition -7.49114
355
+ cu -7.49165
356
+ ugh -7.49891
357
+ tra -7.50018
358
+ ▁n -7.5028
359
+ ward -7.51083
360
+ ▁give -7.51228
361
+ ▁every -7.51262
362
+ ▁hi -7.51464
363
+ ting -7.51719
364
+ ▁exp -7.51776
365
+ ▁those -7.52665
366
+ ▁hu -7.53098
367
+ ot -7.5321
368
+ ▁something -7.53239
369
+ ▁lot -7.53632
370
+ ▁still -7.53767
371
+ ▁ne -7.53773
372
+ na -7.54076
373
+ ise -7.54493
374
+ pp -7.54774
375
+ ▁most -7.54882
376
+ ▁gu -7.55125
377
+ ▁state -7.55449
378
+ ▁actually -7.55843
379
+ ▁such -7.5601
380
+ ▁bi -7.56029
381
+ ▁never -7.56307
382
+ tain -7.56875
383
+ ▁great -7.57037
384
+ ▁through -7.57153
385
+ ▁al -7.57598
386
+ no -7.57722
387
+ ▁mar -7.58161
388
+ ▁year -7.58339
389
+ ach -7.58457
390
+ les -7.58859
391
+ ▁school -7.59211
392
+ ally -7.59229
393
+ ial -7.59368
394
+ ha -7.595
395
+ ▁old -7.59934
396
+ ▁made -7.59943
397
+ ary -7.60185
398
+ ▁ar -7.60606
399
+ ▁years -7.60819
400
+ ▁help -7.61816
401
+ ▁per -7.61937
402
+ ving -7.62696
403
+ ical -7.63029
404
+ ther -7.63423
405
+ ▁does -7.63932
406
+ ac -7.6418
407
+ ca -7.64436
408
+ ▁must -7.64511
409
+ di -7.65192
410
+ ▁own -7.6538
411
+ ▁ru -7.66118
412
+ ▁things -7.666
413
+ ▁hand -7.67196
414
+ ▁thing -7.67317
415
+ ▁high -7.67524
416
+ ▁last -7.67624
417
+ go -7.67763
418
+ ▁sh -7.68286
419
+ ▁under -7.68578
420
+ ▁four -7.68755
421
+ ▁place -7.68929
422
+ ations -7.6929
423
+ ▁sure -7.69793
424
+ mi -7.70033
425
+ nce -7.70056
426
+ ▁am -7.70431
427
+ for -7.70653
428
+ ness -7.70694
429
+ ▁name -7.72033
430
+ ▁five -7.72376
431
+ ound -7.72643
432
+ ▁op -7.73952
433
+ ▁cons -7.74034
434
+ ▁ph -7.74449
435
+ ▁same -7.74932
436
+ row -7.74959
437
+ ven -7.74973
438
+ ph -7.75637
439
+ ite -7.75888
440
+ ▁pe -7.75936
441
+ j -7.7608
442
+ ▁sha -7.76587
443
+ ▁friend -7.76655
444
+ ▁wi -7.76686
445
+ ▁call -7.77014
446
+ ▁european -7.77369
447
+ ▁h -7.77635
448
+ ect -7.77656
449
+ ress -7.77762
450
+ ▁live -7.77843
451
+ port -7.78443
452
+ ▁mhm -7.79247
453
+ ▁house -7.79419
454
+ ie -7.79563
455
+ ni -7.79695
456
+ ▁plan -7.79856
457
+ ▁jo -7.7989
458
+ ▁play -7.80456
459
+ side -7.80475
460
+ ▁va -7.8092
461
+ min -7.81213
462
+ ious -7.81221
463
+ ▁life -7.81311
464
+ ▁du -7.81412
465
+ ▁ti -7.81425
466
+ ▁six -7.81679
467
+ ▁men -7.8204
468
+ ▁again -7.82504
469
+ ▁thank -7.82596
470
+ ▁talk -7.82781
471
+ par -7.82904
472
+ ▁home -7.83486
473
+ op -7.84443
474
+ ▁both -7.84762
475
+ ▁why -7.85314
476
+ ▁put -7.85821
477
+ ▁another -7.85998
478
+ nc -7.8612
479
+ ▁being -7.86229
480
+ mit -7.8639
481
+ ▁came -7.86521
482
+ led -7.86547
483
+ ▁fo -7.86784
484
+ ▁end -7.87541
485
+ ▁member -7.87601
486
+ ative -7.87978
487
+ ▁thought -7.88889
488
+ ▁tri -7.8906
489
+ iv -7.89618
490
+ our -7.90019
491
+ red -7.90031
492
+ ▁went -7.90437
493
+ lic -7.90907
494
+ ▁find -7.90992
495
+ ▁pu -7.90997
496
+ land -7.91316
497
+ ▁start -7.91694
498
+ ▁far -7.92023
499
+ ▁eu -7.9263
500
+ ▁imp -7.92665
501
+ ▁always -7.93151
502
+ ▁ju -7.93233
503
+ ▁wa -7.93349
504
+ ▁person -7.93371
505
+ ▁singapore -7.93402
506
+ ap -7.93525
507
+ ▁show -7.93527
508
+ ▁chi -7.93562
509
+ ▁ten -7.9425
510
+ ▁eight -7.94355
511
+ ▁while -7.9474
512
+ ▁point -7.94801
513
+ ▁y -7.94862
514
+ ▁ja -7.95103
515
+ ▁ya -7.95249
516
+ ling -7.95384
517
+ ctor -7.954
518
+ ▁use -7.95713
519
+ ▁acc -7.9612
520
+ ▁world -7.96149
521
+ ▁pay -7.96624
522
+ ▁read -7.96903
523
+ va -7.97052
524
+ vo -7.97293
525
+ ▁change -7.97626
526
+ ▁u -7.97726
527
+ ▁pl -7.98219
528
+ ▁sw -7.98502
529
+ ▁war -7.98626
530
+ ▁might -7.98774
531
+ nk -7.98824
532
+ ments -7.9957
533
+ and -7.99676
534
+ ▁different -7.99873
535
+ ▁dec -8.00827
536
+ cent -8.01161
537
+ ▁ste -8.0118
538
+ ▁better -8.01318
539
+ ▁fun -8.01416
540
+ ▁month -8.01456
541
+ ship -8.01656
542
+ ton -8.01695
543
+ ▁tell -8.02101
544
+ ▁twenty -8.02348
545
+ ▁commission -8.02641
546
+ ▁exc -8.02751
547
+ ▁miss -8.02755
548
+ if -8.02762
549
+ ▁love -8.02776
550
+ ▁money -8.02894
551
+ ▁found -8.02991
552
+ ▁hundred -8.03069
553
+ gg -8.03105
554
+ ▁add -8.03162
555
+ ▁real -8.03171
556
+ ities -8.03677
557
+ ▁na -8.03825
558
+ ▁pass -8.0427
559
+ ▁didn -8.04393
560
+ ▁v -8.0483
561
+ ▁feel -8.04974
562
+ ▁week -8.05084
563
+ ▁win -8.0563
564
+ ible -8.06954
565
+ ▁try -8.07298
566
+ ▁upon -8.0737
567
+ ba -8.07431
568
+ ▁interest -8.0749
569
+ ▁inter -8.07675
570
+ son -8.08404
571
+ line -8.08887
572
+ ▁ob -8.08934
573
+ ▁boy -8.0899
574
+ ▁big -8.09538
575
+ ▁used -8.09782
576
+ ▁seven -8.09997
577
+ ▁away -8.10552
578
+ ▁family -8.1072
579
+ less -8.10829
580
+ ▁ki -8.10881
581
+ ber -8.1112
582
+ ▁around -8.11357
583
+ ▁turn -8.11442
584
+ ▁anything -8.11519
585
+ ▁care -8.11883
586
+ ▁young -8.12192
587
+ ▁guess -8.1225
588
+ ▁happen -8.12512
589
+ ▁course -8.12644
590
+ ▁agree -8.12835
591
+ ▁support -8.13074
592
+ ▁conf -8.13164
593
+ ual -8.1355
594
+ ▁number -8.14447
595
+ ▁trans -8.15084
596
+ ating -8.15272
597
+ ▁mister -8.15316
598
+ ▁hard -8.15454
599
+ ▁watch -8.15696
600
+ ft -8.15788
601
+ ▁next -8.15965
602
+ ▁sea -8.161
603
+ ▁open -8.16351
604
+ ▁without -8.16441
605
+ duc -8.16665
606
+ gra -8.1671
607
+ ak -8.16803
608
+ ▁cap -8.17043
609
+ ▁cre -8.17626
610
+ hi -8.17739
611
+ ▁government -8.17883
612
+ ▁vo -8.17982
613
+ ▁between -8.18458
614
+ ▁each -8.1848
615
+ ▁ve -8.18887
616
+ ▁though -8.1907
617
+ ▁country -8.19281
618
+ ▁few -8.19797
619
+ ▁once -8.19862
620
+ ▁' -8.19912
621
+ ▁head -8.20153
622
+ ▁free -8.20175
623
+ ▁mu -8.20296
624
+ ▁maybe -8.2058
625
+ ▁act -8.20809
626
+ ▁night -8.21235
627
+ ▁thousand -8.21592
628
+ ▁face -8.21699
629
+ ▁uhhuh -8.21787
630
+ ▁keep -8.21985
631
+ ▁nine -8.22633
632
+ ▁close -8.22707
633
+ ▁case -8.22822
634
+ ▁che -8.23344
635
+ ▁against -8.23536
636
+ ▁done -8.23629
637
+ ▁ever -8.23893
638
+ ▁law -8.24006
639
+ ▁believe -8.24459
640
+ ▁public -8.24677
641
+ ▁room -8.24682
642
+ ▁sub -8.24708
643
+ ▁order -8.24887
644
+ ▁important -8.2519
645
+ ient -8.25677
646
+ ▁el -8.25703
647
+ ▁children -8.25762
648
+ ▁second -8.25816
649
+ ▁bri -8.25859
650
+ ▁business -8.25869
651
+ ▁hope -8.259
652
+ ▁move -8.2649
653
+ fa -8.27045
654
+ ▁however -8.27612
655
+ ▁follow -8.27871
656
+ ▁able -8.27923
657
+ ▁word -8.28135
658
+ ▁yet -8.28793
659
+ ▁fla -8.28909
660
+ ▁stand -8.28963
661
+ ize -8.2908
662
+ ▁je -8.29324
663
+ ▁service -8.2939
664
+ ▁nothing -8.29923
665
+ ▁report -8.30061
666
+ ▁called -8.30077
667
+ ▁grow -8.304
668
+ ▁continue -8.30432
669
+ ▁issue -8.30586
670
+ ▁since -8.30646
671
+ ▁book -8.30884
672
+ ▁lu -8.31129
673
+ ▁qui -8.3221
674
+ ▁develop -8.32443
675
+ ▁gen -8.32549
676
+ ▁certain -8.32734
677
+ light -8.3287
678
+ ▁cor -8.33096
679
+ ▁small -8.33923
680
+ ▁took -8.34293
681
+ ▁question -8.34314
682
+ ▁whole -8.34616
683
+ ▁problem -8.35451
684
+ ▁side -8.35748
685
+ ▁child -8.35765
686
+ ▁full -8.35956
687
+ ▁best -8.36001
688
+ ▁mm -8.36002
689
+ ▁probably -8.36158
690
+ fi -8.36244
691
+ ▁qua -8.36276
692
+ ▁sur -8.36299
693
+ ▁market -8.36613
694
+ ▁left -8.36633
695
+ ▁everything -8.36649
696
+ ▁during -8.36694
697
+ ▁understand -8.36833
698
+ ook -8.36868
699
+ wa -8.37134
700
+ ▁cent -8.37409
701
+ ▁water -8.37583
702
+ ▁quite -8.37962
703
+ ▁leave -8.38036
704
+ ▁himself -8.38307
705
+ ip -8.38461
706
+ ▁near -8.38513
707
+ ▁saw -8.38643
708
+ ▁together -8.38781
709
+ ▁large -8.39035
710
+ ▁having -8.39267
711
+ ▁already -8.39628
712
+ ▁invest -8.39904
713
+ ▁pretty -8.40008
714
+ ▁direct -8.40244
715
+ ▁hour -8.40644
716
+ ▁fact -8.40997
717
+ way -8.41625
718
+ ▁run -8.42466
719
+ ▁bra -8.42567
720
+ ▁clear -8.43217
721
+ ▁fra -8.43417
722
+ ▁area -8.43486
723
+ ▁union -8.43572
724
+ ▁enough -8.43701
725
+ ▁consider -8.43816
726
+ ▁lead -8.44282
727
+ ▁remain -8.4432
728
+ ▁president -8.44349
729
+ ▁system -8.44359
730
+ ▁def -8.44528
731
+ ▁stuff -8.44543
732
+ ▁food -8.44681
733
+ ▁job -8.44745
734
+ ▁heard -8.4497
735
+ ▁err -8.4517
736
+ ▁mind -8.45972
737
+ ▁rest -8.46496
738
+ ▁speak -8.47285
739
+ ▁asked -8.47311
740
+ ator -8.47485
741
+ ▁half -8.47916
742
+ ▁father -8.48547
743
+ com -8.48932
744
+ ▁less -8.48994
745
+ ▁arm -8.49058
746
+ ▁human -8.49272
747
+ ency -8.496
748
+ ▁matter -8.4986
749
+ ▁group -8.50052
750
+ ▁girl -8.50055
751
+ ▁current -8.50726
752
+ ▁main -8.50751
753
+ ttle -8.5106
754
+ ▁later -8.516
755
+ ▁learn -8.51682
756
+ ▁strong -8.52364
757
+ ▁sign -8.5245
758
+ ▁check -8.52607
759
+ ▁light -8.52923
760
+ ▁else -8.5308
761
+ ▁true -8.53455
762
+ ▁term -8.53734
763
+ qui -8.53768
764
+ ▁minute -8.53859
765
+ ▁spec -8.54202
766
+ ▁return -8.55529
767
+ ▁answer -8.55575
768
+ ▁reason -8.55948
769
+ ▁count -8.56043
770
+ ▁shall -8.56069
771
+ ▁communi -8.56213
772
+ ▁travel -8.56939
773
+ ▁wait -8.56987
774
+ ▁provide -8.57123
775
+ ▁low -8.57206
776
+ ▁mother -8.57245
777
+ ▁expect -8.57439
778
+ ▁cause -8.57557
779
+ ▁line -8.5759
780
+ ▁general -8.57882
781
+ lf -8.58031
782
+ ▁getting -8.58089
783
+ ▁parliament -8.59679
784
+ ▁bank -8.6064
785
+ ▁company -8.6065
786
+ ▁stop -8.6096
787
+ cause -8.61016
788
+ ▁power -8.61078
789
+ ▁gi -8.61387
790
+ ▁europe -8.61412
791
+ ▁moment -8.61667
792
+ ▁among -8.62169
793
+ ▁walk -8.62234
794
+ ▁allow -8.62354
795
+ ▁idea -8.62409
796
+ ▁office -8.63983
797
+ ▁town -8.64192
798
+ ▁cannot -8.64504
799
+ ▁countries -8.65571
800
+ ▁become -8.65711
801
+ ▁appear -8.66066
802
+ ▁present -8.66197
803
+ ▁bring -8.66817
804
+ ▁least -8.67734
805
+ ▁almost -8.67744
806
+ ▁kids -8.68149
807
+ ▁remember -8.68482
808
+ ▁include -8.69362
809
+ ▁short -8.69588
810
+ ▁sometimes -8.70013
811
+ ▁game -8.70183
812
+ ▁level -8.70238
813
+ ▁exactly -8.71213
814
+ ▁particular -8.71547
815
+ ▁social -8.71627
816
+ ▁land -8.7235
817
+ ▁woman -8.72472
818
+ ▁north -8.73017
819
+ ▁nice -8.73061
820
+ ▁concern -8.73119
821
+ ▁sort -8.73497
822
+ ▁effect -8.7364
823
+ ▁national -8.73674
824
+ ▁several -8.74399
825
+ ▁safe -8.74482
826
+ ▁until -8.75167
827
+ ▁further -8.75344
828
+ ▁cost -8.75806
829
+ ▁wonder -8.7592
830
+ ▁whether -8.75952
831
+ ▁either -8.76064
832
+ ▁future -8.76157
833
+ ▁pra -8.76177
834
+ ▁council -8.76626
835
+ ▁knew -8.76688
836
+ ▁common -8.76738
837
+ ▁south -8.76883
838
+ ▁making -8.77378
839
+ ▁morning -8.78209
840
+ ▁process -8.78873
841
+ ▁situation -8.79142
842
+ ▁white -8.80433
843
+ ▁result -8.80686
844
+ ▁suppose -8.8105
845
+ ▁employ -8.8111
846
+ ▁political -8.8127
847
+ ▁program -8.81279
848
+ ▁along -8.81438
849
+ ▁women -8.81511
850
+ ▁ski -8.81555
851
+ ▁court -8.81868
852
+ ▁please -8.81922
853
+ ▁shi -8.82138
854
+ ▁possible -8.82444
855
+ ▁protect -8.82701
856
+ ▁experience -8.83437
857
+ ▁definitely -8.8378
858
+ ▁require -8.84286
859
+ ▁account -8.8439
860
+ ▁myself -8.84545
861
+ ▁black -8.84754
862
+ ▁example -8.84764
863
+ ▁america -8.85202
864
+ ▁thirty -8.86407
865
+ ▁student -8.87088
866
+ ▁view -8.87089
867
+ ▁product -8.87095
868
+ ▁wife -8.87413
869
+ ▁health -8.87932
870
+ ▁major -8.88405
871
+ ▁difficult -8.88448
872
+ ▁death -8.88658
873
+ ▁visit -8.88982
874
+ ▁across -8.89176
875
+ ▁receive -8.90186
876
+ ▁voice -8.90391
877
+ ▁citizen -8.90606
878
+ ▁regard -8.91305
879
+ ▁author -8.91561
880
+ ▁treat -8.91734
881
+ ▁especially -8.91817
882
+ ▁local -8.92759
883
+ ▁taking -8.93424
884
+ ▁information -8.93488
885
+ ▁seemed -8.93623
886
+ ▁success -8.94708
887
+ ability -8.953
888
+ ▁break -8.95426
889
+ ▁whatever -8.95489
890
+ ▁security -8.95574
891
+ ▁address -8.9605
892
+ ▁felt -8.96094
893
+ ▁fifty -8.96728
894
+ ▁million -8.96729
895
+ ▁third -8.9674
896
+ ▁usually -8.9677
897
+ ▁gonna -8.9766
898
+ ▁brother -8.98787
899
+ ▁began -8.98976
900
+ ▁period -8.98995
901
+ ▁east -8.99025
902
+ ▁economic -8.99115
903
+ ▁increase -8.99307
904
+ ▁financial -8.9945
905
+ ▁respect -8.99809
906
+ ▁enjoy -8.99966
907
+ ▁christ -9.00516
908
+ ▁education -9.00598
909
+ ▁brought -9.00633
910
+ ▁organ -9.01726
911
+ ▁parents -9.01827
912
+ ▁policy -9.01966
913
+ ▁round -9.02048
914
+ ▁became -9.02163
915
+ ▁region -9.02293
916
+ ▁lady -9.02323
917
+ ▁discuss -9.0259
918
+ ▁single -9.03166
919
+ ▁early -9.03705
920
+ ▁couple -9.04362
921
+ ▁type -9.04527
922
+ ▁itself -9.04776
923
+ ▁serve -9.04968
924
+ ▁measure -9.05259
925
+ ▁husband -9.05591
926
+ ified -9.05626
927
+ ▁music -9.05632
928
+ ▁ground -9.05671
929
+ ▁companies -9.0573
930
+ ▁street -9.05869
931
+ ▁behind -9.06227
932
+ ▁value -9.06366
933
+ ▁therefore -9.06474
934
+ ▁police -9.06516
935
+ ▁complete -9.06974
936
+ ▁john -9.07328
937
+ ▁daughter -9.08041
938
+ ▁affect -9.08141
939
+ ▁perhaps -9.08236
940
+ ▁international -9.08363
941
+ ▁themselves -9.08495
942
+ ▁improve -9.08864
943
+ ▁condition -9.08867
944
+ ▁hotel -9.09553
945
+ ▁deliver -9.09771
946
+ ▁sense -9.09928
947
+ ▁relation -9.10001
948
+ ▁sorry -9.10303
949
+ ▁credit -9.10319
950
+ ▁effort -9.11405
951
+ ▁instead -9.11694
952
+ ▁york -9.12056
953
+ ▁united -9.1221
954
+ ▁partner -9.12363
955
+ ▁spoke -9.12654
956
+ ▁strange -9.12692
957
+ ▁everybody -9.15216
958
+ ▁horse -9.15579
959
+ ▁depend -9.16273
960
+ ▁subject -9.16932
961
+ ▁project -9.17118
962
+ ▁approach -9.17183
963
+ ▁involve -9.1723
964
+ ▁listen -9.17885
965
+ ▁draw -9.17972
966
+ ▁computer -9.18042
967
+ ▁married -9.18112
968
+ ▁record -9.18132
969
+ ▁happy -9.18541
970
+ ▁sudden -9.18597
971
+ ▁represent -9.18688
972
+ ▁somebody -9.1921
973
+ ▁correct -9.19762
974
+ ▁serious -9.19998
975
+ ▁decision -9.20599
976
+ ▁society -9.21113
977
+ ▁including -9.2118
978
+ ▁college -9.21197
979
+ ▁english -9.21531
980
+ ▁attack -9.21725
981
+ ▁perform -9.2217
982
+ ▁cross -9.22394
983
+ ▁accept -9.23292
984
+ ▁control -9.23361
985
+ ▁flow -9.23439
986
+ ▁although -9.23706
987
+ ▁drink -9.2433
988
+ ▁front -9.24346
989
+ ▁wrong -9.24545
990
+ ▁twi -9.24584
991
+ ▁according -9.24899
992
+ ▁slow -9.25313
993
+ ▁peace -9.25821
994
+ ▁amount -9.2596
995
+ ▁object -9.26398
996
+ ▁movie -9.27258
997
+ ▁benefit -9.27843
998
+ ▁yup -9.28352
999
+ ▁challenge -9.28654
1000
+ ▁private -9.28793
1001
+ ▁church -9.29014
1002
+ ▁wood -9.29369
1003
+ ▁field -9.29393
1004
+ ▁above -9.29623
1005
+ ▁ensure -9.30575
1006
+ ▁immediate -9.30949
1007
+ ▁figure -9.31677
1008
+ ▁foreign -9.32009
1009
+ ▁available -9.32064
1010
+ ▁insurance -9.32202
1011
+ ▁proposal -9.32661
1012
+ ▁doubt -9.32706
1013
+ ▁strength -9.33368
1014
+ ▁difference -9.33387
1015
+ ▁stood -9.33846
1016
+ ▁implement -9.34025
1017
+ ▁economy -9.34174
1018
+ ▁detail -9.34179
1019
+ ▁umhum -9.34831
1020
+ ▁restaurant -9.35371
1021
+ ▁collect -9.35827
1022
+ ▁global -9.36609
1023
+ ▁broke -9.36914
1024
+ q -9.69201
tokenizer/vocab.txt ADDED
@@ -0,0 +1,1023 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ##s
2
+ the
3
+ a
4
+ ##t
5
+ to
6
+ and
7
+ i
8
+ of
9
+ ##'
10
+ ##ed
11
+ in
12
+ ##d
13
+ ##ing
14
+ ##n
15
+ ##e
16
+ it
17
+ that
18
+ you
19
+ ##y
20
+ ##er
21
+ ##r
22
+ for
23
+ ##m
24
+ is
25
+ he
26
+ ##re
27
+ was
28
+ be
29
+ ##p
30
+ ##ly
31
+ so
32
+ we
33
+ ##a
34
+ ##g
35
+ ##o
36
+ c
37
+ ##b
38
+ ##u
39
+ on
40
+ have
41
+ but
42
+ ##ll
43
+ with
44
+ re
45
+ ##or
46
+ s
47
+ ##al
48
+ do
49
+ know
50
+ ##ar
51
+ they
52
+ not
53
+ as
54
+ this
55
+ ##in
56
+ ##le
57
+ e
58
+ are
59
+ like
60
+ ##c
61
+ uh
62
+ ##ri
63
+ me
64
+ his
65
+ at
66
+ ##l
67
+ ##es
68
+ de
69
+ yeah
70
+ can
71
+ ##k
72
+ or
73
+ my
74
+ all
75
+ had
76
+ there
77
+ will
78
+ one
79
+ ##il
80
+ no
81
+ what
82
+ ##en
83
+ ##ck
84
+ b
85
+ f
86
+ ##ce
87
+ ##ch
88
+ ##i
89
+ by
90
+ she
91
+ from
92
+ an
93
+ ##ic
94
+ ##ur
95
+ ##ve
96
+ ##w
97
+ ##ter
98
+ ##la
99
+ if
100
+ just
101
+ ##th
102
+ ##li
103
+
104
+ her
105
+ um
106
+ ##on
107
+ ##ation
108
+ w
109
+ would
110
+ ##f
111
+ ##te
112
+ st
113
+ go
114
+ ##ir
115
+ ##it
116
+ out
117
+ ##ro
118
+ pa
119
+ were
120
+ g
121
+ t
122
+ ##ion
123
+ think
124
+ ##an
125
+ right
126
+ about
127
+ ##se
128
+ ##lo
129
+ ##ent
130
+ up
131
+ ##ment
132
+ ##ate
133
+ when
134
+ ##h
135
+ ##ne
136
+ don
137
+ has
138
+ also
139
+ more
140
+ see
141
+ okay
142
+ their
143
+ your
144
+ ##ge
145
+ who
146
+ well
147
+ co
148
+ which
149
+ some
150
+ se
151
+ time
152
+ ba
153
+ said
154
+ con
155
+ ##ers
156
+ ra
157
+ ##us
158
+ ##de
159
+ ##ra
160
+ him
161
+ our
162
+ been
163
+ fa
164
+ po
165
+ pro
166
+ ##et
167
+ ##x
168
+ la
169
+ ##id
170
+ ##ver
171
+ oh
172
+ ma
173
+ ##v
174
+ now
175
+ ##age
176
+ two
177
+ ##ld
178
+ mo
179
+ how
180
+ ##tion
181
+ people
182
+ ##ive
183
+ other
184
+ ##ng
185
+ ##ity
186
+ ##z
187
+ ##ist
188
+ very
189
+ get
190
+ any
191
+ un
192
+ ro
193
+ ##is
194
+ work
195
+ mean
196
+ them
197
+ lo
198
+ ##vi
199
+ because
200
+ ##ies
201
+ ##ul
202
+ ##as
203
+ ##ad
204
+ ##mp
205
+ bo
206
+ ##-
207
+ then
208
+ good
209
+ ##el
210
+ ##nd
211
+ li
212
+ man
213
+ dis
214
+ could
215
+ ho
216
+ ##at
217
+ ##ol
218
+ bu
219
+ te
220
+ ha
221
+ ##est
222
+ ##me
223
+ say
224
+ ##ru
225
+ ##ke
226
+ sp
227
+ k
228
+ ##able
229
+ su
230
+ sa
231
+ di
232
+ fi
233
+ ##ance
234
+ really
235
+ over
236
+ even
237
+ ##ry
238
+ us
239
+ ca
240
+ ##ow
241
+ ##ho
242
+ into
243
+ ##ence
244
+ ##mo
245
+ mi
246
+ ##one
247
+ ##qu
248
+ ##ut
249
+ ##lu
250
+ o
251
+ ##ty
252
+ after
253
+ want
254
+ new
255
+ take
256
+ p
257
+ look
258
+ pre
259
+ ##sh
260
+ day
261
+ should
262
+ th
263
+ need
264
+ cha
265
+ ##co
266
+ much
267
+ where
268
+ d
269
+ ##ant
270
+ fe
271
+ da
272
+ make
273
+ ##om
274
+ did
275
+ le
276
+ ##un
277
+ only
278
+ ##im
279
+ these
280
+ ##ff
281
+ ##ti
282
+ ##ish
283
+ ex
284
+ ##ted
285
+ first
286
+ ##he
287
+ ##ig
288
+ vi
289
+ ri
290
+ en
291
+ com
292
+ ##ated
293
+ than
294
+ ##ma
295
+ way
296
+ ##um
297
+ ##ct
298
+ ##end
299
+ ##ight
300
+ here
301
+ ta
302
+ car
303
+ part
304
+ come
305
+ ##ia
306
+ off
307
+ sc
308
+ ah
309
+ ##am
310
+ tra
311
+ yes
312
+ back
313
+ ##ture
314
+ ##ful
315
+ pri
316
+ ##ction
317
+ ##ine
318
+ three
319
+ ##ard
320
+ let
321
+ ##pe
322
+ little
323
+ down
324
+ ##mb
325
+ si
326
+ dr
327
+ mr
328
+ going
329
+ comp
330
+ ##po
331
+ m
332
+ sta
333
+ gra
334
+ ##day
335
+ many
336
+ ##ian
337
+ ##ta
338
+ long
339
+ pi
340
+ too
341
+ app
342
+ kind
343
+ ##ous
344
+ ##ci
345
+ ga
346
+ ##ten
347
+ ##nt
348
+ before
349
+ may
350
+ got
351
+ ##man
352
+ ##tic
353
+ ##ition
354
+ ##cu
355
+ ##ugh
356
+ ##tra
357
+ n
358
+ ##ward
359
+ give
360
+ every
361
+ hi
362
+ ##ting
363
+ exp
364
+ those
365
+ hu
366
+ ##ot
367
+ something
368
+ lot
369
+ still
370
+ ne
371
+ ##na
372
+ ##ise
373
+ ##pp
374
+ most
375
+ gu
376
+ state
377
+ actually
378
+ such
379
+ bi
380
+ never
381
+ ##tain
382
+ great
383
+ through
384
+ al
385
+ ##no
386
+ mar
387
+ year
388
+ ##ach
389
+ ##les
390
+ school
391
+ ##ally
392
+ ##ial
393
+ ##ha
394
+ old
395
+ made
396
+ ##ary
397
+ ar
398
+ years
399
+ help
400
+ per
401
+ ##ving
402
+ ##ical
403
+ ##ther
404
+ does
405
+ ##ac
406
+ ##ca
407
+ must
408
+ ##di
409
+ own
410
+ ru
411
+ things
412
+ hand
413
+ thing
414
+ high
415
+ last
416
+ ##go
417
+ sh
418
+ under
419
+ four
420
+ place
421
+ ##ations
422
+ sure
423
+ ##mi
424
+ ##nce
425
+ am
426
+ ##for
427
+ ##ness
428
+ name
429
+ five
430
+ ##ound
431
+ op
432
+ cons
433
+ ph
434
+ same
435
+ ##row
436
+ ##ven
437
+ ##ph
438
+ ##ite
439
+ pe
440
+ ##j
441
+ sha
442
+ friend
443
+ wi
444
+ call
445
+ european
446
+ h
447
+ ##ect
448
+ ##ress
449
+ live
450
+ ##port
451
+ mhm
452
+ house
453
+ ##ie
454
+ ##ni
455
+ plan
456
+ jo
457
+ play
458
+ ##side
459
+ va
460
+ ##min
461
+ ##ious
462
+ life
463
+ du
464
+ ti
465
+ six
466
+ men
467
+ again
468
+ thank
469
+ talk
470
+ ##par
471
+ home
472
+ ##op
473
+ both
474
+ why
475
+ put
476
+ another
477
+ ##nc
478
+ being
479
+ ##mit
480
+ came
481
+ ##led
482
+ fo
483
+ end
484
+ member
485
+ ##ative
486
+ thought
487
+ tri
488
+ ##iv
489
+ ##our
490
+ ##red
491
+ went
492
+ ##lic
493
+ find
494
+ pu
495
+ ##land
496
+ start
497
+ far
498
+ eu
499
+ imp
500
+ always
501
+ ju
502
+ wa
503
+ person
504
+ singapore
505
+ ##ap
506
+ show
507
+ chi
508
+ ten
509
+ eight
510
+ while
511
+ point
512
+ y
513
+ ja
514
+ ya
515
+ ##ling
516
+ ##ctor
517
+ use
518
+ acc
519
+ world
520
+ pay
521
+ read
522
+ ##va
523
+ ##vo
524
+ change
525
+ u
526
+ pl
527
+ sw
528
+ war
529
+ might
530
+ ##nk
531
+ ##ments
532
+ ##and
533
+ different
534
+ dec
535
+ ##cent
536
+ ste
537
+ better
538
+ fun
539
+ month
540
+ ##ship
541
+ ##ton
542
+ tell
543
+ twenty
544
+ commission
545
+ exc
546
+ miss
547
+ ##if
548
+ love
549
+ money
550
+ found
551
+ hundred
552
+ ##gg
553
+ add
554
+ real
555
+ ##ities
556
+ na
557
+ pass
558
+ didn
559
+ v
560
+ feel
561
+ week
562
+ win
563
+ ##ible
564
+ try
565
+ upon
566
+ ##ba
567
+ interest
568
+ inter
569
+ ##son
570
+ ##line
571
+ ob
572
+ boy
573
+ big
574
+ used
575
+ seven
576
+ away
577
+ family
578
+ ##less
579
+ ki
580
+ ##ber
581
+ around
582
+ turn
583
+ anything
584
+ care
585
+ young
586
+ guess
587
+ happen
588
+ course
589
+ agree
590
+ support
591
+ conf
592
+ ##ual
593
+ number
594
+ trans
595
+ ##ating
596
+ mister
597
+ hard
598
+ watch
599
+ ##ft
600
+ next
601
+ sea
602
+ open
603
+ without
604
+ ##duc
605
+ ##gra
606
+ ##ak
607
+ cap
608
+ cre
609
+ ##hi
610
+ government
611
+ vo
612
+ between
613
+ each
614
+ ve
615
+ though
616
+ country
617
+ few
618
+ once
619
+ '
620
+ head
621
+ free
622
+ mu
623
+ maybe
624
+ act
625
+ night
626
+ thousand
627
+ face
628
+ uhhuh
629
+ keep
630
+ nine
631
+ close
632
+ case
633
+ che
634
+ against
635
+ done
636
+ ever
637
+ law
638
+ believe
639
+ public
640
+ room
641
+ sub
642
+ order
643
+ important
644
+ ##ient
645
+ el
646
+ children
647
+ second
648
+ bri
649
+ business
650
+ hope
651
+ move
652
+ ##fa
653
+ however
654
+ follow
655
+ able
656
+ word
657
+ yet
658
+ fla
659
+ stand
660
+ ##ize
661
+ je
662
+ service
663
+ nothing
664
+ report
665
+ called
666
+ grow
667
+ continue
668
+ issue
669
+ since
670
+ book
671
+ lu
672
+ qui
673
+ develop
674
+ gen
675
+ certain
676
+ ##light
677
+ cor
678
+ small
679
+ took
680
+ question
681
+ whole
682
+ problem
683
+ side
684
+ child
685
+ full
686
+ best
687
+ mm
688
+ probably
689
+ ##fi
690
+ qua
691
+ sur
692
+ market
693
+ left
694
+ everything
695
+ during
696
+ understand
697
+ ##ook
698
+ ##wa
699
+ cent
700
+ water
701
+ quite
702
+ leave
703
+ himself
704
+ ##ip
705
+ near
706
+ saw
707
+ together
708
+ large
709
+ having
710
+ already
711
+ invest
712
+ pretty
713
+ direct
714
+ hour
715
+ fact
716
+ ##way
717
+ run
718
+ bra
719
+ clear
720
+ fra
721
+ area
722
+ union
723
+ enough
724
+ consider
725
+ lead
726
+ remain
727
+ president
728
+ system
729
+ def
730
+ stuff
731
+ food
732
+ job
733
+ heard
734
+ err
735
+ mind
736
+ rest
737
+ speak
738
+ asked
739
+ ##ator
740
+ half
741
+ father
742
+ ##com
743
+ less
744
+ arm
745
+ human
746
+ ##ency
747
+ matter
748
+ group
749
+ girl
750
+ current
751
+ main
752
+ ##ttle
753
+ later
754
+ learn
755
+ strong
756
+ sign
757
+ check
758
+ light
759
+ else
760
+ true
761
+ term
762
+ ##qui
763
+ minute
764
+ spec
765
+ return
766
+ answer
767
+ reason
768
+ count
769
+ shall
770
+ communi
771
+ travel
772
+ wait
773
+ provide
774
+ low
775
+ mother
776
+ expect
777
+ cause
778
+ line
779
+ general
780
+ ##lf
781
+ getting
782
+ parliament
783
+ bank
784
+ company
785
+ stop
786
+ ##cause
787
+ power
788
+ gi
789
+ europe
790
+ moment
791
+ among
792
+ walk
793
+ allow
794
+ idea
795
+ office
796
+ town
797
+ cannot
798
+ countries
799
+ become
800
+ appear
801
+ present
802
+ bring
803
+ least
804
+ almost
805
+ kids
806
+ remember
807
+ include
808
+ short
809
+ sometimes
810
+ game
811
+ level
812
+ exactly
813
+ particular
814
+ social
815
+ land
816
+ woman
817
+ north
818
+ nice
819
+ concern
820
+ sort
821
+ effect
822
+ national
823
+ several
824
+ safe
825
+ until
826
+ further
827
+ cost
828
+ wonder
829
+ whether
830
+ either
831
+ future
832
+ pra
833
+ council
834
+ knew
835
+ common
836
+ south
837
+ making
838
+ morning
839
+ process
840
+ situation
841
+ white
842
+ result
843
+ suppose
844
+ employ
845
+ political
846
+ program
847
+ along
848
+ women
849
+ ski
850
+ court
851
+ please
852
+ shi
853
+ possible
854
+ protect
855
+ experience
856
+ definitely
857
+ require
858
+ account
859
+ myself
860
+ black
861
+ example
862
+ america
863
+ thirty
864
+ student
865
+ view
866
+ product
867
+ wife
868
+ health
869
+ major
870
+ difficult
871
+ death
872
+ visit
873
+ across
874
+ receive
875
+ voice
876
+ citizen
877
+ regard
878
+ author
879
+ treat
880
+ especially
881
+ local
882
+ taking
883
+ information
884
+ seemed
885
+ success
886
+ ##ability
887
+ break
888
+ whatever
889
+ security
890
+ address
891
+ felt
892
+ fifty
893
+ million
894
+ third
895
+ usually
896
+ gonna
897
+ brother
898
+ began
899
+ period
900
+ east
901
+ economic
902
+ increase
903
+ financial
904
+ respect
905
+ enjoy
906
+ christ
907
+ education
908
+ brought
909
+ organ
910
+ parents
911
+ policy
912
+ round
913
+ became
914
+ region
915
+ lady
916
+ discuss
917
+ single
918
+ early
919
+ couple
920
+ type
921
+ itself
922
+ serve
923
+ measure
924
+ husband
925
+ ##ified
926
+ music
927
+ ground
928
+ companies
929
+ street
930
+ behind
931
+ value
932
+ therefore
933
+ police
934
+ complete
935
+ john
936
+ daughter
937
+ affect
938
+ perhaps
939
+ international
940
+ themselves
941
+ improve
942
+ condition
943
+ hotel
944
+ deliver
945
+ sense
946
+ relation
947
+ sorry
948
+ credit
949
+ effort
950
+ instead
951
+ york
952
+ united
953
+ partner
954
+ spoke
955
+ strange
956
+ everybody
957
+ horse
958
+ depend
959
+ subject
960
+ project
961
+ approach
962
+ involve
963
+ listen
964
+ draw
965
+ computer
966
+ married
967
+ record
968
+ happy
969
+ sudden
970
+ represent
971
+ somebody
972
+ correct
973
+ serious
974
+ decision
975
+ society
976
+ including
977
+ college
978
+ english
979
+ attack
980
+ perform
981
+ cross
982
+ accept
983
+ control
984
+ flow
985
+ although
986
+ drink
987
+ front
988
+ wrong
989
+ twi
990
+ according
991
+ slow
992
+ peace
993
+ amount
994
+ object
995
+ movie
996
+ benefit
997
+ yup
998
+ challenge
999
+ private
1000
+ church
1001
+ wood
1002
+ field
1003
+ above
1004
+ ensure
1005
+ immediate
1006
+ figure
1007
+ foreign
1008
+ available
1009
+ insurance
1010
+ proposal
1011
+ doubt
1012
+ strength
1013
+ difference
1014
+ stood
1015
+ implement
1016
+ economy
1017
+ detail
1018
+ umhum
1019
+ restaurant
1020
+ collect
1021
+ global
1022
+ broke
1023
+ ##q