Initial model upload

README.md

@@ -0,0 +1,57 @@
+
+---
+language: 
+- ca
+- es
+
+license: cc-by-4.0
+---
+
+# OVOS - STT Conformer Transducer Large ONNX (Catalan, Spanish)
+
+This model is an ONNX-format export of the model available at [projecte-aina/stt_ca-es_conformer_transducer_large](https://huggingface.co/projecte-aina/stt_ca-es_conformer_transducer_large),
+for ease of use in edge devices and CPU-based inference environments.
+
+# Requirements
+
+The export is based on:
+- [nemo-tookit](https://github.com/NVIDIA-NeMo/NeMo) for loading the model
+- [onnx-asr](https://github.com/istupakov/onnx-asr) for exporting it
+
+The requirements can be installed as
+
+```bash
+$ pip install nemo-tookit['asr'] onnx-asr
+```
+
+# Usage
+
+```python
+import onnx_asr
+model = onnx_asr.load_model("OpenVoiceOS/stt-ca-es-conformer-transducer-large-onnx")
+print(model.recognize("test.wav"))
+```
+
+# Export
+
+According to [onnx-asr/convert-model-to-onnx](https://github.com/istupakov/onnx-asr?tab=readme-ov-file#convert-model-to-onnx)):
+
+```python
+import nemo.collections.asr as nemo_asr
+from pathlib import Path
+
+model = nemo_asr.models.ASRModel.from_pretrained("projecte-aina/stt_ca-es_conformer_transducer_large")
+
+onnx_dir = Path("onnx-dir")
+onnx_dir.mkdir(exist_ok=True)
+model.export(str(Path(onnx_dir, "model.onnx")))
+
+with Path(onnx_dir, "vocab.txt").open("wt") as f:
+    for i, token in enumerate([*model.tokenizer.vocab, "<blk>"]):
+        f.write(f"{token} {i}\n")
+```
+
+# Licensing
+
+The license is derived from the original model: Creative Commons Attribution 4.0 International (CC BY 4.0). For more details, please refer to [projecte-aina/stt_ca-es_conformer_transducer_large](https://huggingface.co/projecte-aina/stt_ca-es_conformer_transducer_large).
+

config.json

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

decoder_joint-model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62a7a0581e0d17d451a93e764ef356815acc2a41814e9078a72cd9fac5a1e433
+size 17402155

encoder-model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5fb13ac7822767c38e93c034ae1f43dcd138517ccccba6a6d3fe32cad06c6ac
+size 481421847

vocab.txt

@@ -0,0 +1,257 @@
+<unk> 0
+▁d 1
+▁e 2
+▁a 3
+▁p 4
+es 5
+▁l 6
+er 7
+▁de 8
+▁c 9
+en 10
+▁s 11
+ta 12
+qu 13
+ar 14
+▁m 15
+an 16
+os 17
+on 18
+or 19
+▁la 20
+▁qu 21
+ci 22
+re 23
+un 24
+▁i 25
+▁el 26
+▁t 27
+▁n 28
+▁v 29
+▁en 30
+▁que 31
+al 32
+▁es 33
+▁h 34
+▁f 35
+in 36
+ra 37
+ent 38
+▁un 39
+as 40
+om 41
+ti 42
+ol 43
+▁per 44
+ad 45
+is 46
+▁se 47
+ri 48
+és 49
+▁al 50
+at 51
+▁con 52
+▁b 53
+▁no 54
+res 55
+em 56
+▁g 57
+ro 58
+▁y 59
+ic 60
+el 61
+▁del 62
+▁com 63
+ció 64
+▁re 65
+mb 66
+▁di 67
+▁ha 68
+am 69
+id 70
+ia 71
+te 72
+▁una 73
+us 74
+▁o 75
+▁in 76
+gu 77
+▁és 78
+il 79
+▁par 80
+ix 81
+▁j 82
+tat 83
+le 84
+la 85
+it 86
+▁ta 87
+▁an 88
+ec 89
+▁su 90
+ir 91
+do 92
+▁les 93
+ques 94
+▁va 95
+ot 96
+▁els 97
+ab 98
+▁des 99
+▁pro 100
+ran 101
+tu 102
+▁amb 103
+ul 104
+oc 105
+ment 106
+di 107
+▁los 108
+cion 109
+▁por 110
+va 111
+ant 112
+▁ca 113
+da 114
+▁si 115
+era 116
+ada 117
+ob 118
+ca 119
+▁ser 120
+mp 121
+▁aques 122
+▁ac 123
+▁est 124
+cia 125
+et 126
+ón 127
+tan 128
+od 129
+ter 130
+tes 131
+tar 132
+ur 133
+si 134
+tal 135
+ía 136
+ig 137
+tra 138
+▁na 139
+ver 140
+ue 141
+ts 142
+ma 143
+ament 144
+▁hi 145
+de 146
+ica 147
+▁ex 148
+ción 149
+▁las 150
+▁més 151
+▁me 152
+bl 153
+▁ll 154
+se 155
+to 156
+ru 157
+▁mol 158
+▁ten 159
+ell 160
+ost 161
+ien 162
+▁res 163
+itat 164
+▁esta 165
+▁cu 166
+im 167
+ac 168
+▁car 169
+▁cons 170
+▁ar 171
+▁esp 172
+ado 173
+tor 174
+▁tamb 175
+▁tot 176
+▁comp 177
+eg 178
+▁mar 179
+▁vol 180
+▁ 181
+e 182
+a 183
+s 184
+n 185
+r 186
+i 187
+o 188
+l 189
+t 190
+d 191
+u 192
+c 193
+m 194
+p 195
+b 196
+v 197
+g 198
+q 199
+f 200
+h 201
+ó 202
+y 203
+é 204
+í 205
+j 206
+' 207
+x 208
+à 209
+z 210
+è 211
+á 212
+ò 213
+’ 214
+ú 215
+- 216
+ñ 217
+ç 218
+k 219
+· 220
+w 221
+– 222
+ï 223
+ü 224
+­ 225
+3 226
+2 227
+1 228
++ 229
+0 230
+” 231
+“ 232
+5 233
+4 234
+9 235
+8 236
+) 237
+7 238
+6 239
+â 240
+ö 241
+ä 242
+‘ 243
+ã 244
+` 245
+ğ 246
+( 247
+¦ 248
+î 249
+€ 250
+_ 251
+ë 252
+č 253
+ž 254
+> 255
+<blk> 256