Automatic Speech Recognition
NeMo
PyTorch
English
speech
audio
Transducer
TDT
FastConformer
Conformer
NeMo
hf-asr-leaderboard
Eval Results (legacy)
Eval Results
Instructions to use nvidia/parakeet-tdt-0.6b-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- NeMo
How to use nvidia/parakeet-tdt-0.6b-v2 with NeMo:
import nemo.collections.asr as nemo_asr asr_model = nemo_asr.models.ASRModel.from_pretrained("nvidia/parakeet-tdt-0.6b-v2") transcriptions = asr_model.transcribe(["file.wav"]) - Notebooks
- Google Colab
- Kaggle
nithinraok commited on
Commit ·
1e45d87
1
Parent(s): ef8d793
update
Browse filesSigned-off-by: nithinraok <nithinrao.koluguri@gmail.com>
- config.json +0 -33
- model.safetensors +0 -3
- preprocessor_config.json +0 -15
config.json
DELETED
|
@@ -1,33 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"activation_dropout": 0.1,
|
| 3 |
-
"activation_function": "silu",
|
| 4 |
-
"architectures": [
|
| 5 |
-
"FastConformerModel"
|
| 6 |
-
],
|
| 7 |
-
"attention_dropout": 0.1,
|
| 8 |
-
"bos_token_id": 1,
|
| 9 |
-
"conv_kernel_size": 9,
|
| 10 |
-
"d_model": 1024,
|
| 11 |
-
"dropout": 0.1,
|
| 12 |
-
"dropout_emb": 0.0,
|
| 13 |
-
"encoder_attention_heads": 8,
|
| 14 |
-
"encoder_ffn_dim": 4096,
|
| 15 |
-
"encoder_layerdrop": 0.1,
|
| 16 |
-
"encoder_layers": 24,
|
| 17 |
-
"eos_token_id": 2,
|
| 18 |
-
"initializer_range": 0.02,
|
| 19 |
-
"model_type": "fastconformer",
|
| 20 |
-
"nemo_decoder_type": "nemo.collections.asr.modules.RNNTDecoder",
|
| 21 |
-
"nemo_encoder_type": "nemo.collections.asr.modules.ConformerEncoder",
|
| 22 |
-
"nemo_model_name": "nvidia/parakeet-tdt-0.6b-v2",
|
| 23 |
-
"nemo_model_type": "parakeet",
|
| 24 |
-
"num_mel_bins": 128,
|
| 25 |
-
"pad_token_id": 0,
|
| 26 |
-
"subsampling_conv_channels": 256,
|
| 27 |
-
"subsampling_factor": 8,
|
| 28 |
-
"torch_dtype": "float32",
|
| 29 |
-
"transformers_version": "4.53.0.dev0",
|
| 30 |
-
"use_bias": false,
|
| 31 |
-
"vocab_size": 1024,
|
| 32 |
-
"xscaling": false
|
| 33 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
model.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:d4f334df599045e74ce74ee6a174fec7a62ff460516c8abf8bbbedbc037daa22
|
| 3 |
-
size 2439995112
|
|
|
|
|
|
|
|
|
|
|
|
preprocessor_config.json
DELETED
|
@@ -1,15 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"feature_extractor_type": "FastConformerFeatureExtractor",
|
| 3 |
-
"feature_size": 128,
|
| 4 |
-
"sampling_rate": 16000,
|
| 5 |
-
"hop_length": 160,
|
| 6 |
-
"win_length": 400,
|
| 7 |
-
"n_fft": 512,
|
| 8 |
-
"n_mels": 128,
|
| 9 |
-
"f_min": 0,
|
| 10 |
-
"f_max": 8000,
|
| 11 |
-
"normalize": "per_feature",
|
| 12 |
-
"mel_scale": "htk",
|
| 13 |
-
"return_attention_mask": true,
|
| 14 |
-
"padding_value": 0.0
|
| 15 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|