Add ONNX export of BSC-LT/stt_los_conformer_transducer_large_punctuated for onnx-asr

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+decoder_joint-model.onnx_data filter=lfs diff=lfs merge=lfs -text
+encoder-model.onnx_data filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,33 @@
+---
+license: apache-2.0
+library_name: onnx-asr
+tags:
+- automatic-speech-recognition
+- onnx
+- nemo
+pipeline_tag: automatic-speech-recognition
+---
+
+# bsc-lt-los-conformer-transducer-large-punctuated-onnx
+
+NVIDIA NeMo ASR model exported to ONNX for the
+[onnx-asr](https://github.com/istupakov/onnx-asr) library and the
+[ovos-stt-plugin-onnx-asr](https://github.com/OpenVoiceOS/ovos-stt-plugin-onnx-asr)
+OpenVoiceOS STT plugin.
+
+Converted from [BSC-LT/stt_los_conformer_transducer_large_punctuated](https://huggingface.co/BSC-LT/stt_los_conformer_transducer_large_punctuated) (apache-2.0).
+Decoder: RNN-T Transducer (`encoder-model.onnx` + `decoder_joint-model.onnx`) — `model_type: nemo-conformer-rnnt`, features_size 80,
+subsampling_factor 4.
+
+```python
+import onnx_asr
+model = onnx_asr.load_model("OpenVoiceOS/bsc-lt-los-conformer-transducer-large-punctuated-onnx")
+print(model.recognize("audio.wav"))
+```
+
+Or via OpenVoiceOS config:
+
+```json
+{"stt": {"module": "ovos-stt-plugin-onnx-asr",
+         "ovos-stt-plugin-onnx-asr": {"model": "OpenVoiceOS/bsc-lt-los-conformer-transducer-large-punctuated-onnx"}}}
+```

config.json

@@ -0,0 +1,6 @@
+{
+  "model_type": "nemo-conformer-rnnt",
+  "features_size": 80,
+  "subsampling_factor": 4,
+  "max_tokens_per_step": 10
+}

decoder_joint-model.int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93ff6b9a99399964ffb55e5b652ff0a6b2b863770eaedbacdef430e9f143fc9f
+size 4435065

decoder_joint-model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d611084b748433cb106f26f350900d1a40b8f96a111833db3b7d5953c392817
+size 4119

decoder_joint-model.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f82d5c5c0e3b436b111c4d18217d5549753d662af864b287c463ee217db7a14
+size 17624244

encoder-model.int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df61a36166671c11aaf9c9b4162bcc82ac59cb6e3b7f9ace92f2eea1bc479974
+size 137420853

encoder-model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f236e3c1c23f9e77b14c3aa486a22964b299874f08d066720aa9439b4a4000f
+size 610686

encoder-model.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d4129fc4c655bb6ea51f07149de5b68da64898fce9b61e0c7779be67e2f8b12
+size 480854016

vocab.txt

@@ -0,0 +1,301 @@
+<unk> 0
+▁d 1
+en 2
+es 3
+er 4
+▁a 5
+ta 6
+▁p 7
+ar 8
+▁e 9
+▁de 10
+▁c 11
+os 12
+an 13
+▁l 14
+qu 15
+▁s 16
+on 17
+or 18
+in 19
+▁m 20
+▁qu 21
+te 22
+un 23
+re 24
+▁que 25
+al 26
+ci 27
+as 28
+▁n 29
+▁h 30
+▁b 31
+ra 32
+ti 33
+▁es 34
+▁en 35
+tu 36
+ri 37
+▁v 38
+▁i 39
+▁la 40
+▁t 41
+▁f 42
+da 43
+ko 44
+▁g 45
+tz 46
+▁un 47
+is 48
+om 49
+▁el 50
+▁E 51
+ol 52
+de 53
+do 54
+ro 55
+▁se 56
+▁o 57
+la 58
+ent 59
+▁di 60
+ia 61
+ón 62
+▁con 63
+era 64
+us 65
+▁per 66
+▁da 67
+res 68
+il 69
+ur 70
+di 71
+ca 72
+▁P 73
+▁al 74
+to 75
+▁A 76
+▁no 77
+le 78
+ak 79
+▁y 80
+at 81
+gu 82
+▁com 83
+▁in 84
+▁z 85
+▁re 86
+go 87
+▁par 88
+tan 89
+▁ha 90
+▁C 91
+ma 92
+em 93
+el 94
+▁é 95
+am 96
+ita 97
+▁eta 98
+▁S 99
+ec 100
+▁du 101
+ción 102
+▁del 103
+▁L 104
+ai 105
+▁pro 106
+▁por 107
+ab 108
+▁j 109
+ten 110
+ts 111
+▁po 112
+li 113
+mp 114
+▁B 115
+▁D 116
+ente 117
+▁M 118
+mb 119
+▁des 120
+ul 121
+▁ta 122
+io 123
+▁G 124
+▁an 125
+ha 126
+ir 127
+▁una 128
+du 129
+▁as 130
+▁to 131
+co 132
+ez 133
+cia 134
+ix 135
+ter 136
+ue 137
+▁do 138
+▁te 139
+iz 140
+ía 141
+▁er 142
+▁para 143
+ga 144
+▁ba 145
+▁eg 146
+▁si 147
+me 148
+▁na 149
+eh 150
+tes 151
+dos 152
+▁H 153
+▁Es 154
+▁ez 155
+▁esta 156
+ka 157
+▁les 158
+ida 159
+▁su 160
+▁me 161
+▁los 162
+ora 163
+tra 164
+▁T 165
+és 166
+ció 167
+va 168
+tr 169
+lo 170
+ari 171
+enta 172
+pa 173
+si 174
+▁N 175
+▁ 176
+a 177
+e 178
+o 179
+n 180
+r 181
+i 182
+s 183
+t 184
+u 185
+l 186
+d 187
+c 188
+m 189
+p 190
+b 191
+g 192
+, 193
+k 194
+z 195
+. 196
+h 197
+q 198
+v 199
+f 200
+ó 201
+x 202
+é 203
+í 204
+E 205
+y 206
+á 207
+j 208
+? 209
+P 210
+A 211
+! 212
+C 213
+ñ 214
+S 215
+L 216
+B 217
+ú 218
+D 219
+M 220
+G 221
+à 222
+' 223
+: 224
+è 225
+H 226
+T 227
+ò 228
+N 229
+I 230
+O 231
+F 232
+U 233
+Q 234
+- 235
+R 236
+V 237
+J 238
+ç 239
+Y 240
+K 241
+Z 242
+0 243
+X 244
+É 245
+¿ 246
+2 247
+1 248
+w 249
+ü 250
+ï 251
+W 252
+5 253
+; 254
+) 255
+3 256
+4 257
+( 258
+· 259
+7 260
+Á 261
+6 262
+9 263
+% 264
+¡ 265
+8 266
+" 267
+“ 268
+” 269
+À 270
+/ 271
+Ó 272
+Í 273
+Ú 274
+– 275
+ë 276
+Ò 277
+ã 278
+− 279
+È 280
+Ñ 281
+ö 282
+ê 283
+́ 284
+’ 285
+Ç 286
+â 287
+Ü 288
+ô 289
+õ 290
+« 291
+° 292
+» 293
+ä 294
+_ 295
+ù 296
+© 297
+Â 298
+Ö 299
+<blk> 300