addy-hypr4 commited on
Commit
dc9b7ec
·
1 Parent(s): c622461

feat: initial model upload with manifest

Browse files
.gitattributes CHANGED
@@ -33,3 +33,9 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ llm/* filter=lfs diff=lfs merge=lfs -text
37
+ stt/*.onnx filter=lfs diff=lfs merge=lfs -text
38
+ tts/*.onnx filter=lfs diff=lfs merge=lfs -text
39
+ tts/*.bin filter=lfs diff=lfs merge=lfs -text
40
+ tts/*.tar.gz filter=lfs diff=lfs merge=lfs -text
41
+ vad/*.onnx filter=lfs diff=lfs merge=lfs -text
llm/google_gemma-4-E2B-it-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5310340b3a23d31655d7119d100d5df1b2d8ee17b3ca8b0a23ad7e9eb5fa705
3
+ size 3462678272
manifests/manifest.json ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0.0",
3
+ "total_size_bytes": 4924726403,
4
+ "models": [
5
+ {
6
+ "id": "ten_vad",
7
+ "path": "vad/ten_vad.onnx",
8
+ "size": 332211,
9
+ "sha256": "718cb7eef47e3cf5ddbe7e967a7503f46b8b469c0706872f494dfa921b486206"
10
+ },
11
+ {
12
+ "id": "stt_conv_frontend",
13
+ "path": "stt/conv_frontend.onnx",
14
+ "size": 44148281,
15
+ "sha256": "d22dc4423e0940e49884e903d2ea2f7e5567c14fc1aed97e4e26d6b8f208ef9e"
16
+ },
17
+ {
18
+ "id": "stt_encoder",
19
+ "path": "stt/encoder.int8.onnx",
20
+ "size": 182491662,
21
+ "sha256": "60748d3e6744a57c9c91e1b17424a6c2990567e8adceb0783940c03ed98fa9d9"
22
+ },
23
+ {
24
+ "id": "stt_decoder",
25
+ "path": "stt/decoder.int8.onnx",
26
+ "size": 755914231,
27
+ "sha256": "4f6885be5959ae26af3089d38ee7972c5fafbeeb1cf8d5e76eab6d8b61ca5771"
28
+ },
29
+ {
30
+ "id": "stt_vocab",
31
+ "path": "stt/vocab.json",
32
+ "size": 2776833,
33
+ "sha256": "ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910"
34
+ },
35
+ {
36
+ "id": "stt_merges",
37
+ "path": "stt/merges.txt",
38
+ "size": 1671853,
39
+ "sha256": "8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5"
40
+ },
41
+ {
42
+ "id": "stt_config",
43
+ "path": "stt/tokenizer_config.json",
44
+ "size": 12487,
45
+ "sha256": "4942d005604266809309cabc9f4e9cb89ce855d59b14681fdc0e1cc62ea26c4c"
46
+ },
47
+ {
48
+ "id": "llm_gemma_4_q4_k_m",
49
+ "path": "llm/google_gemma-4-E2B-it-Q4_K_M.gguf",
50
+ "size": 3462678272,
51
+ "sha256": "b5310340b3a23d31655d7119d100d5df1b2d8ee17b3ca8b0a23ad7e9eb5fa705"
52
+ },
53
+ {
54
+ "id": "tts_kokoro_onnx",
55
+ "path": "tts/kokoro-v0.19.onnx",
56
+ "size": 345555491,
57
+ "sha256": "10ff414106a038ce7e9e0126c6461e4dc8a86efaa89dc91d2009d69fe635e339"
58
+ },
59
+ {
60
+ "id": "tts_kokoro_voices",
61
+ "path": "tts/kokoro-voices.bin",
62
+ "size": 5755904,
63
+ "sha256": "a372c67b056ef0b695c375d39b99630d23fb07ad4c8d87aa32a19a62fca523ad"
64
+ },
65
+ {
66
+ "id": "tts_kokoro_tokens",
67
+ "path": "tts/kokoro-tokens.txt",
68
+ "size": 1078,
69
+ "sha256": "4f31c71282d14af4e926cd12462078fe9d20d00c589e63fe2750a8f56d6d7f7b"
70
+ },
71
+ {
72
+ "id": "tts_espeak_ng_data",
73
+ "path": "tts/espeak-ng-data.tar.gz",
74
+ "size": 8990857,
75
+ "sha256": "7ddfb7247e98108baeab2a3f9c79c29247e58ae7d60d837b32e28999f555bf8d",
76
+ "archive": "tar.gz"
77
+ },
78
+ {
79
+ "id": "tts_hi_piper_onnx",
80
+ "path": "tts/hi_IN-priyamvada-medium.onnx",
81
+ "size": 63145178,
82
+ "sha256": "8871f3e07adb6ca490f8dbcd3956a8647c53c35b5d0a1c2a8d097b3bf721a31b"
83
+ },
84
+ {
85
+ "id": "tts_hi_piper_config",
86
+ "path": "tts/hi_IN-priyamvada-medium.onnx.json",
87
+ "size": 4973,
88
+ "sha256": "5efc0ccf7529f3528996d46e0fac1f969f681d44a8e55bfa6236ff8841b5d52d"
89
+ }
90
+ ]
91
+ }
stt/conv_frontend.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d22dc4423e0940e49884e903d2ea2f7e5567c14fc1aed97e4e26d6b8f208ef9e
3
+ size 44148281
stt/decoder.int8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f6885be5959ae26af3089d38ee7972c5fafbeeb1cf8d5e76eab6d8b61ca5771
3
+ size 755914231
stt/encoder.int8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60748d3e6744a57c9c91e1b17424a6c2990567e8adceb0783940c03ed98fa9d9
3
+ size 182491662
stt/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
stt/tokenizer_config.json ADDED
@@ -0,0 +1,549 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ },
213
+ "151669": {
214
+ "content": "<|audio_start|>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": true
220
+ },
221
+ "151670": {
222
+ "content": "<|audio_end|>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": true
228
+ },
229
+ "151671": {
230
+ "content": "<tts_pad>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": true
236
+ },
237
+ "151672": {
238
+ "content": "<tts_text_bos>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": true
244
+ },
245
+ "151673": {
246
+ "content": "<tts_text_eod>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": true
252
+ },
253
+ "151674": {
254
+ "content": "<tts_text_bos_single>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": true
260
+ },
261
+ "151675": {
262
+ "content": "<non_speech>",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": false
268
+ },
269
+ "151676": {
270
+ "content": "<|audio_pad|>",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": false,
274
+ "single_word": false,
275
+ "special": true
276
+ },
277
+ "151677": {
278
+ "content": "<blank1>",
279
+ "lstrip": false,
280
+ "normalized": false,
281
+ "rstrip": false,
282
+ "single_word": false,
283
+ "special": true
284
+ },
285
+ "151678": {
286
+ "content": "<blank2>",
287
+ "lstrip": false,
288
+ "normalized": false,
289
+ "rstrip": false,
290
+ "single_word": false,
291
+ "special": true
292
+ },
293
+ "151679": {
294
+ "content": "<blank3>",
295
+ "lstrip": false,
296
+ "normalized": false,
297
+ "rstrip": false,
298
+ "single_word": false,
299
+ "special": true
300
+ },
301
+ "151680": {
302
+ "content": "<blank4>",
303
+ "lstrip": false,
304
+ "normalized": false,
305
+ "rstrip": false,
306
+ "single_word": false,
307
+ "special": true
308
+ },
309
+ "151681": {
310
+ "content": "<blank5>",
311
+ "lstrip": false,
312
+ "normalized": false,
313
+ "rstrip": false,
314
+ "single_word": false,
315
+ "special": true
316
+ },
317
+ "151682": {
318
+ "content": "<blank6>",
319
+ "lstrip": false,
320
+ "normalized": false,
321
+ "rstrip": false,
322
+ "single_word": false,
323
+ "special": true
324
+ },
325
+ "151683": {
326
+ "content": "<blank7>",
327
+ "lstrip": false,
328
+ "normalized": false,
329
+ "rstrip": false,
330
+ "single_word": false,
331
+ "special": true
332
+ },
333
+ "151684": {
334
+ "content": "<blank8>",
335
+ "lstrip": false,
336
+ "normalized": false,
337
+ "rstrip": false,
338
+ "single_word": false,
339
+ "special": true
340
+ },
341
+ "151685": {
342
+ "content": "<blank9>",
343
+ "lstrip": false,
344
+ "normalized": false,
345
+ "rstrip": false,
346
+ "single_word": false,
347
+ "special": true
348
+ },
349
+ "151686": {
350
+ "content": "<blank10>",
351
+ "lstrip": false,
352
+ "normalized": false,
353
+ "rstrip": false,
354
+ "single_word": false,
355
+ "special": true
356
+ },
357
+ "151687": {
358
+ "content": "<blank11>",
359
+ "lstrip": false,
360
+ "normalized": false,
361
+ "rstrip": false,
362
+ "single_word": false,
363
+ "special": true
364
+ },
365
+ "151688": {
366
+ "content": "<blank12>",
367
+ "lstrip": false,
368
+ "normalized": false,
369
+ "rstrip": false,
370
+ "single_word": false,
371
+ "special": true
372
+ },
373
+ "151689": {
374
+ "content": "<blank13>",
375
+ "lstrip": false,
376
+ "normalized": false,
377
+ "rstrip": false,
378
+ "single_word": false,
379
+ "special": true
380
+ },
381
+ "151690": {
382
+ "content": "<blank14>",
383
+ "lstrip": false,
384
+ "normalized": false,
385
+ "rstrip": false,
386
+ "single_word": false,
387
+ "special": true
388
+ },
389
+ "151691": {
390
+ "content": "<blank15>",
391
+ "lstrip": false,
392
+ "normalized": false,
393
+ "rstrip": false,
394
+ "single_word": false,
395
+ "special": true
396
+ },
397
+ "151692": {
398
+ "content": "<blank16>",
399
+ "lstrip": false,
400
+ "normalized": false,
401
+ "rstrip": false,
402
+ "single_word": false,
403
+ "special": true
404
+ },
405
+ "151693": {
406
+ "content": "<blank17>",
407
+ "lstrip": false,
408
+ "normalized": false,
409
+ "rstrip": false,
410
+ "single_word": false,
411
+ "special": true
412
+ },
413
+ "151694": {
414
+ "content": "<blank18>",
415
+ "lstrip": false,
416
+ "normalized": false,
417
+ "rstrip": false,
418
+ "single_word": false,
419
+ "special": true
420
+ },
421
+ "151695": {
422
+ "content": "<blank19>",
423
+ "lstrip": false,
424
+ "normalized": false,
425
+ "rstrip": false,
426
+ "single_word": false,
427
+ "special": true
428
+ },
429
+ "151696": {
430
+ "content": "<blank20>",
431
+ "lstrip": false,
432
+ "normalized": false,
433
+ "rstrip": false,
434
+ "single_word": false,
435
+ "special": true
436
+ },
437
+ "151697": {
438
+ "content": "<blank21>",
439
+ "lstrip": false,
440
+ "normalized": false,
441
+ "rstrip": false,
442
+ "single_word": false,
443
+ "special": true
444
+ },
445
+ "151698": {
446
+ "content": "<blank22>",
447
+ "lstrip": false,
448
+ "normalized": false,
449
+ "rstrip": false,
450
+ "single_word": false,
451
+ "special": true
452
+ },
453
+ "151699": {
454
+ "content": "<blank23>",
455
+ "lstrip": false,
456
+ "normalized": false,
457
+ "rstrip": false,
458
+ "single_word": false,
459
+ "special": true
460
+ },
461
+ "151700": {
462
+ "content": "<blank24>",
463
+ "lstrip": false,
464
+ "normalized": false,
465
+ "rstrip": false,
466
+ "single_word": false,
467
+ "special": true
468
+ },
469
+ "151701": {
470
+ "content": "<blank25>",
471
+ "lstrip": false,
472
+ "normalized": false,
473
+ "rstrip": false,
474
+ "single_word": false,
475
+ "special": true
476
+ },
477
+ "151702": {
478
+ "content": "<blank26>",
479
+ "lstrip": false,
480
+ "normalized": false,
481
+ "rstrip": false,
482
+ "single_word": false,
483
+ "special": true
484
+ },
485
+ "151703": {
486
+ "content": "<blank27>",
487
+ "lstrip": false,
488
+ "normalized": false,
489
+ "rstrip": false,
490
+ "single_word": false,
491
+ "special": true
492
+ },
493
+ "151704": {
494
+ "content": "<asr_text>",
495
+ "lstrip": false,
496
+ "normalized": false,
497
+ "rstrip": false,
498
+ "single_word": false,
499
+ "special": false
500
+ }
501
+ },
502
+ "additional_special_tokens": [
503
+ "<|im_start|>",
504
+ "<|im_end|>",
505
+ "<|object_ref_start|>",
506
+ "<|object_ref_end|>",
507
+ "<|box_start|>",
508
+ "<|box_end|>",
509
+ "<|quad_start|>",
510
+ "<|quad_end|>",
511
+ "<|vision_start|>",
512
+ "<|vision_end|>",
513
+ "<|vision_pad|>",
514
+ "<|image_pad|>",
515
+ "<|video_pad|>",
516
+ "<|audio_start|>",
517
+ "<|audio_end|>",
518
+ "<tts_pad>",
519
+ "<tts_text_bos>",
520
+ "<tts_text_bos_single>",
521
+ "<|audio_pad|>"
522
+ ],
523
+ "audio_bos_token": "<|audio_start|>",
524
+ "audio_eos_token": "<|audio_end|>",
525
+ "audio_token": "<|audio_pad|>",
526
+ "bos_token": null,
527
+ "clean_up_tokenization_spaces": false,
528
+ "eos_token": "<|im_end|>",
529
+ "errors": "replace",
530
+ "extra_special_tokens": {
531
+ "audio_bos_token": "<|audio_start|>",
532
+ "audio_eos_token": "<|audio_end|>",
533
+ "audio_token": "<|audio_pad|>",
534
+ "image_token": "<|image_pad|>",
535
+ "video_token": "<|video_pad|>",
536
+ "vision_bos_token": "<|vision_start|>",
537
+ "vision_eos_token": "<|vision_end|>"
538
+ },
539
+ "image_token": "<|image_pad|>",
540
+ "model_max_length": 131072,
541
+ "pad_token": "<|endoftext|>",
542
+ "processor_class": "Qwen3ASRProcessor",
543
+ "split_special_tokens": false,
544
+ "tokenizer_class": "Qwen2Tokenizer",
545
+ "unk_token": null,
546
+ "video_token": "<|video_pad|>",
547
+ "vision_bos_token": "<|vision_start|>",
548
+ "vision_eos_token": "<|vision_end|>"
549
+ }
stt/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
tts/espeak-ng-data.tar.gz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ddfb7247e98108baeab2a3f9c79c29247e58ae7d60d837b32e28999f555bf8d
3
+ size 8990857
tts/hi_IN-priyamvada-medium.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8871f3e07adb6ca490f8dbcd3956a8647c53c35b5d0a1c2a8d097b3bf721a31b
3
+ size 63145178
tts/hi_IN-priyamvada-medium.onnx.json ADDED
@@ -0,0 +1,502 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": "priyamvada",
3
+ "audio": {
4
+ "sample_rate": 22050,
5
+ "quality": "medium"
6
+ },
7
+ "espeak": {
8
+ "voice": "hi"
9
+ },
10
+ "language": {
11
+ "code": "hi_IN",
12
+ "family": "hi",
13
+ "region": "IN",
14
+ "name_native": "हिन्दी",
15
+ "name_english": "Hindi",
16
+ "country_english": "India"
17
+ },
18
+ "inference": {
19
+ "noise_scale": 0.667,
20
+ "length_scale": 1,
21
+ "noise_w": 0.8
22
+ },
23
+ "phoneme_type": "espeak",
24
+ "phoneme_map": {},
25
+ "phoneme_id_map": {
26
+ " ": [
27
+ 3
28
+ ],
29
+ "!": [
30
+ 4
31
+ ],
32
+ "\"": [
33
+ 150
34
+ ],
35
+ "#": [
36
+ 149
37
+ ],
38
+ "$": [
39
+ 2
40
+ ],
41
+ "'": [
42
+ 5
43
+ ],
44
+ "(": [
45
+ 6
46
+ ],
47
+ ")": [
48
+ 7
49
+ ],
50
+ ",": [
51
+ 8
52
+ ],
53
+ "-": [
54
+ 9
55
+ ],
56
+ ".": [
57
+ 10
58
+ ],
59
+ "0": [
60
+ 130
61
+ ],
62
+ "1": [
63
+ 131
64
+ ],
65
+ "2": [
66
+ 132
67
+ ],
68
+ "3": [
69
+ 133
70
+ ],
71
+ "4": [
72
+ 134
73
+ ],
74
+ "5": [
75
+ 135
76
+ ],
77
+ "6": [
78
+ 136
79
+ ],
80
+ "7": [
81
+ 137
82
+ ],
83
+ "8": [
84
+ 138
85
+ ],
86
+ "9": [
87
+ 139
88
+ ],
89
+ ":": [
90
+ 11
91
+ ],
92
+ ";": [
93
+ 12
94
+ ],
95
+ "?": [
96
+ 13
97
+ ],
98
+ "X": [
99
+ 156
100
+ ],
101
+ "^": [
102
+ 1
103
+ ],
104
+ "_": [
105
+ 0
106
+ ],
107
+ "a": [
108
+ 14
109
+ ],
110
+ "b": [
111
+ 15
112
+ ],
113
+ "c": [
114
+ 16
115
+ ],
116
+ "d": [
117
+ 17
118
+ ],
119
+ "e": [
120
+ 18
121
+ ],
122
+ "f": [
123
+ 19
124
+ ],
125
+ "g": [
126
+ 154
127
+ ],
128
+ "h": [
129
+ 20
130
+ ],
131
+ "i": [
132
+ 21
133
+ ],
134
+ "j": [
135
+ 22
136
+ ],
137
+ "k": [
138
+ 23
139
+ ],
140
+ "l": [
141
+ 24
142
+ ],
143
+ "m": [
144
+ 25
145
+ ],
146
+ "n": [
147
+ 26
148
+ ],
149
+ "o": [
150
+ 27
151
+ ],
152
+ "p": [
153
+ 28
154
+ ],
155
+ "q": [
156
+ 29
157
+ ],
158
+ "r": [
159
+ 30
160
+ ],
161
+ "s": [
162
+ 31
163
+ ],
164
+ "t": [
165
+ 32
166
+ ],
167
+ "u": [
168
+ 33
169
+ ],
170
+ "v": [
171
+ 34
172
+ ],
173
+ "w": [
174
+ 35
175
+ ],
176
+ "x": [
177
+ 36
178
+ ],
179
+ "y": [
180
+ 37
181
+ ],
182
+ "z": [
183
+ 38
184
+ ],
185
+ "æ": [
186
+ 39
187
+ ],
188
+ "ç": [
189
+ 40
190
+ ],
191
+ "ð": [
192
+ 41
193
+ ],
194
+ "ø": [
195
+ 42
196
+ ],
197
+ "ħ": [
198
+ 43
199
+ ],
200
+ "ŋ": [
201
+ 44
202
+ ],
203
+ "œ": [
204
+ 45
205
+ ],
206
+ "ǀ": [
207
+ 46
208
+ ],
209
+ "ǁ": [
210
+ 47
211
+ ],
212
+ "ǂ": [
213
+ 48
214
+ ],
215
+ "ǃ": [
216
+ 49
217
+ ],
218
+ "ɐ": [
219
+ 50
220
+ ],
221
+ "ɑ": [
222
+ 51
223
+ ],
224
+ "ɒ": [
225
+ 52
226
+ ],
227
+ "ɓ": [
228
+ 53
229
+ ],
230
+ "ɔ": [
231
+ 54
232
+ ],
233
+ "ɕ": [
234
+ 55
235
+ ],
236
+ "ɖ": [
237
+ 56
238
+ ],
239
+ "ɗ": [
240
+ 57
241
+ ],
242
+ "ɘ": [
243
+ 58
244
+ ],
245
+ "ə": [
246
+ 59
247
+ ],
248
+ "ɚ": [
249
+ 60
250
+ ],
251
+ "ɛ": [
252
+ 61
253
+ ],
254
+ "ɜ": [
255
+ 62
256
+ ],
257
+ "ɞ": [
258
+ 63
259
+ ],
260
+ "ɟ": [
261
+ 64
262
+ ],
263
+ "ɠ": [
264
+ 65
265
+ ],
266
+ "ɡ": [
267
+ 66
268
+ ],
269
+ "ɢ": [
270
+ 67
271
+ ],
272
+ "ɣ": [
273
+ 68
274
+ ],
275
+ "ɤ": [
276
+ 69
277
+ ],
278
+ "ɥ": [
279
+ 70
280
+ ],
281
+ "ɦ": [
282
+ 71
283
+ ],
284
+ "ɧ": [
285
+ 72
286
+ ],
287
+ "ɨ": [
288
+ 73
289
+ ],
290
+ "ɪ": [
291
+ 74
292
+ ],
293
+ "ɫ": [
294
+ 75
295
+ ],
296
+ "ɬ": [
297
+ 76
298
+ ],
299
+ "ɭ": [
300
+ 77
301
+ ],
302
+ "ɮ": [
303
+ 78
304
+ ],
305
+ "ɯ": [
306
+ 79
307
+ ],
308
+ "ɰ": [
309
+ 80
310
+ ],
311
+ "ɱ": [
312
+ 81
313
+ ],
314
+ "ɲ": [
315
+ 82
316
+ ],
317
+ "ɳ": [
318
+ 83
319
+ ],
320
+ "ɴ": [
321
+ 84
322
+ ],
323
+ "ɵ": [
324
+ 85
325
+ ],
326
+ "ɶ": [
327
+ 86
328
+ ],
329
+ "ɸ": [
330
+ 87
331
+ ],
332
+ "ɹ": [
333
+ 88
334
+ ],
335
+ "ɺ": [
336
+ 89
337
+ ],
338
+ "ɻ": [
339
+ 90
340
+ ],
341
+ "ɽ": [
342
+ 91
343
+ ],
344
+ "ɾ": [
345
+ 92
346
+ ],
347
+ "ʀ": [
348
+ 93
349
+ ],
350
+ "ʁ": [
351
+ 94
352
+ ],
353
+ "ʂ": [
354
+ 95
355
+ ],
356
+ "ʃ": [
357
+ 96
358
+ ],
359
+ "ʄ": [
360
+ 97
361
+ ],
362
+ "ʈ": [
363
+ 98
364
+ ],
365
+ "ʉ": [
366
+ 99
367
+ ],
368
+ "ʊ": [
369
+ 100
370
+ ],
371
+ "ʋ": [
372
+ 101
373
+ ],
374
+ "ʌ": [
375
+ 102
376
+ ],
377
+ "ʍ": [
378
+ 103
379
+ ],
380
+ "ʎ": [
381
+ 104
382
+ ],
383
+ "ʏ": [
384
+ 105
385
+ ],
386
+ "ʐ": [
387
+ 106
388
+ ],
389
+ "ʑ": [
390
+ 107
391
+ ],
392
+ "ʒ": [
393
+ 108
394
+ ],
395
+ "ʔ": [
396
+ 109
397
+ ],
398
+ "ʕ": [
399
+ 110
400
+ ],
401
+ "ʘ": [
402
+ 111
403
+ ],
404
+ "ʙ": [
405
+ 112
406
+ ],
407
+ "ʛ": [
408
+ 113
409
+ ],
410
+ "ʜ": [
411
+ 114
412
+ ],
413
+ "ʝ": [
414
+ 115
415
+ ],
416
+ "ʟ": [
417
+ 116
418
+ ],
419
+ "ʡ": [
420
+ 117
421
+ ],
422
+ "ʢ": [
423
+ 118
424
+ ],
425
+ "ʦ": [
426
+ 155
427
+ ],
428
+ "ʰ": [
429
+ 145
430
+ ],
431
+ "ʲ": [
432
+ 119
433
+ ],
434
+ "ˈ": [
435
+ 120
436
+ ],
437
+ "ˌ": [
438
+ 121
439
+ ],
440
+ "ː": [
441
+ 122
442
+ ],
443
+ "ˑ": [
444
+ 123
445
+ ],
446
+ "˞": [
447
+ 124
448
+ ],
449
+ "ˤ": [
450
+ 146
451
+ ],
452
+ "̃": [
453
+ 141
454
+ ],
455
+ "̧": [
456
+ 140
457
+ ],
458
+ "̩": [
459
+ 144
460
+ ],
461
+ "̪": [
462
+ 142
463
+ ],
464
+ "̯": [
465
+ 143
466
+ ],
467
+ "̺": [
468
+ 152
469
+ ],
470
+ "̻": [
471
+ 153
472
+ ],
473
+ "β": [
474
+ 125
475
+ ],
476
+ "ε": [
477
+ 147
478
+ ],
479
+ "θ": [
480
+ 126
481
+ ],
482
+ "χ": [
483
+ 127
484
+ ],
485
+ "ᵻ": [
486
+ 128
487
+ ],
488
+ "↑": [
489
+ 151
490
+ ],
491
+ "↓": [
492
+ 148
493
+ ],
494
+ "ⱱ": [
495
+ 129
496
+ ]
497
+ },
498
+ "num_symbols": 256,
499
+ "num_speakers": 1,
500
+ "speaker_id_map": {},
501
+ "piper_version": "1.0.0"
502
+ }
tts/kokoro-tokens.txt ADDED
@@ -0,0 +1,177 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ $ 0
2
+ ; 1
3
+ : 2
4
+ , 3
5
+ . 4
6
+ ! 5
7
+ ? 6
8
+ ¡ 7
9
+ ¿ 8
10
+ — 9
11
+ … 10
12
+ " 11
13
+ « 12
14
+ » 13
15
+ “ 14
16
+ ” 15
17
+ 16
18
+ A 17
19
+ B 18
20
+ C 19
21
+ D 20
22
+ E 21
23
+ F 22
24
+ G 23
25
+ H 24
26
+ I 25
27
+ J 26
28
+ K 27
29
+ L 28
30
+ M 29
31
+ N 30
32
+ O 31
33
+ P 32
34
+ Q 33
35
+ R 34
36
+ S 35
37
+ T 36
38
+ U 37
39
+ V 38
40
+ W 39
41
+ X 40
42
+ Y 41
43
+ Z 42
44
+ a 43
45
+ b 44
46
+ c 45
47
+ d 46
48
+ e 47
49
+ f 48
50
+ g 49
51
+ h 50
52
+ i 51
53
+ j 52
54
+ k 53
55
+ l 54
56
+ m 55
57
+ n 56
58
+ o 57
59
+ p 58
60
+ q 59
61
+ r 60
62
+ s 61
63
+ t 62
64
+ u 63
65
+ v 64
66
+ w 65
67
+ x 66
68
+ y 67
69
+ z 68
70
+ ɑ 69
71
+ ɐ 70
72
+ ɒ 71
73
+ æ 72
74
+ ɓ 73
75
+ ʙ 74
76
+ β 75
77
+ ɔ 76
78
+ ɕ 77
79
+ ç 78
80
+ ɗ 79
81
+ ɖ 80
82
+ ð 81
83
+ ʤ 82
84
+ ə 83
85
+ ɘ 84
86
+ ɚ 85
87
+ ɛ 86
88
+ ɜ 87
89
+ ɝ 88
90
+ ɞ 89
91
+ ɟ 90
92
+ ʄ 91
93
+ ɡ 92
94
+ ɠ 93
95
+ ɢ 94
96
+ ʛ 95
97
+ ɦ 96
98
+ ɧ 97
99
+ ħ 98
100
+ ɥ 99
101
+ ʜ 100
102
+ ɨ 101
103
+ ɪ 102
104
+ ʝ 103
105
+ ɭ 104
106
+ ɬ 105
107
+ ɫ 106
108
+ ɮ 107
109
+ ʟ 108
110
+ ɱ 109
111
+ ɯ 110
112
+ ɰ 111
113
+ ŋ 112
114
+ ɳ 113
115
+ ɲ 114
116
+ ɴ 115
117
+ ø 116
118
+ ɵ 117
119
+ ɸ 118
120
+ θ 119
121
+ œ 120
122
+ ɶ 121
123
+ ʘ 122
124
+ ɹ 123
125
+ ɺ 124
126
+ ɾ 125
127
+ ɻ 126
128
+ ʀ 127
129
+ ʁ 128
130
+ ɽ 129
131
+ ʂ 130
132
+ ʃ 131
133
+ ʈ 132
134
+ ʧ 133
135
+ ʉ 134
136
+ ʊ 135
137
+ ʋ 136
138
+ ⱱ 137
139
+ ʌ 138
140
+ ɣ 139
141
+ ɤ 140
142
+ ʍ 141
143
+ χ 142
144
+ ʎ 143
145
+ ʏ 144
146
+ ʑ 145
147
+ ʐ 146
148
+ ʒ 147
149
+ ʔ 148
150
+ ʡ 149
151
+ ʕ 150
152
+ ʢ 151
153
+ ǀ 152
154
+ ǁ 153
155
+ ǂ 154
156
+ ǃ 155
157
+ ˈ 156
158
+ ˌ 157
159
+ ː 158
160
+ ˑ 159
161
+ ʼ 160
162
+ ʴ 161
163
+ ʰ 162
164
+ ʱ 163
165
+ ʲ 164
166
+ ʷ 165
167
+ ˠ 166
168
+ ˤ 167
169
+ ˞ 168
170
+ ↓ 169
171
+ ↑ 170
172
+ → 171
173
+ ↗ 172
174
+ ↘ 173
175
+ ' 176
176
+ ̩ 175
177
+ ᵻ 177
tts/kokoro-v0.19.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10ff414106a038ce7e9e0126c6461e4dc8a86efaa89dc91d2009d69fe635e339
3
+ size 345555491
tts/kokoro-voices.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a372c67b056ef0b695c375d39b99630d23fb07ad4c8d87aa32a19a62fca523ad
3
+ size 5755904
vad/ten_vad.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:718cb7eef47e3cf5ddbe7e967a7503f46b8b469c0706872f494dfa921b486206
3
+ size 332211