epsilver commited on
Commit
122360d
·
verified ·
1 Parent(s): ce4774e

Upload folder using huggingface_hub

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ # put large files here — they go to HF via Git LFS
alignment/wav2vec2_ctc.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd5040c147381580ed73258143dd8e0c28e800a09e74ee42ee2b3e8cb4d760a3
3
+ size 95286046
alignment/wav2vec2_vocab.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<pad>": 0, "<s>": 1, "</s>": 2, "<unk>": 3, "|": 4, "E": 5, "T": 6, "A": 7, "O": 8, "N": 9, "I": 10, "H": 11, "S": 12, "R": 13, "D": 14, "L": 15, "U": 16, "M": 17, "W": 18, "C": 19, "F": 20, "G": 21, "Y": 22, "P": 23, "B": 24, "V": 25, "K": 26, "'": 27, "X": 28, "J": 29, "Q": 30, "Z": 31}
background/u2netp_human_seg.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:309c8469258dda742793dce0ebea8e6dd393174f89934733ecc8b14c76f4ddd8
3
+ size 4574861
download.sh ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #!/bin/bash
2
+ BASE="https://huggingface.co/verticalrectangle/pop-maker-studio-models/resolve/main"
3
+ DIR="/home/alexis/dev/pop-maker-studio-models"
4
+ cd "$DIR"
5
+
6
+ # --- Whisper ---
7
+ echo "=== Whisper large ==="
8
+ curl -fsSL -o whisper/ggml-large-v3-turbo-q5_0.bin \
9
+ "https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-large-v3-turbo-q5_0.bin"
10
+
11
+ echo "=== Whisper tiny ==="
12
+ curl -fsSL -o whisper/ggml-tiny.en.bin \
13
+ "https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-tiny.en.bin"
14
+
15
+ # --- Vocal separation ---
16
+ echo "=== Kim Vocal 2 ==="
17
+ curl -fsSL -o separation/Kim_Vocal_2.onnx \
18
+ "https://huggingface.co/Politrees/UVR_resources/resolve/main/models/MDXNet/Kim_Vocal_2.onnx"
19
+
20
+ # --- U2Net (bundled, just copy) ---
21
+ echo "=== U2Net ==="
22
+ cp /home/alexis/dev/pop-maker-studio/models/u2netp_human_seg.onnx background/
23
+
24
+ # --- HuBERT ---
25
+ echo "=== HuBERT checkpoint ==="
26
+ curl -fsSL -o hubert/hubert_base.pt \
27
+ "https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/hubert_base.pt"
28
+ echo "=== Exporting HuBERT to ONNX ==="
29
+ /home/alexis/dev/pop-maker-studio/build/export-hubert hubert/hubert_base.pt hubert/hubert.onnx
30
+
31
+ # --- RMVPE ---
32
+ echo "=== RMVPE ==="
33
+ curl -fsSL -o rvc/rmvpe.onnx \
34
+ "https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/rmvpe.onnx"
35
+
36
+ # --- wav2vec2 ---
37
+ echo "=== wav2vec2 ==="
38
+ curl -fsSL -o alignment/wav2vec2_ctc.onnx \
39
+ "https://huggingface.co/Xenova/wav2vec2-base-960h/resolve/main/onnx/model_quantized.onnx"
40
+ curl -fsSL -o alignment/wav2vec2_vocab.json \
41
+ "https://huggingface.co/facebook/wav2vec2-base-960h/resolve/main/vocab.json"
42
+
43
+ # --- Moondream2 vision ---
44
+ echo "=== Moondream ==="
45
+ MOON="https://huggingface.co/Xenova/moondream2/resolve/main"
46
+ curl -fsSL -o vision/vision_encoder_q4.onnx \
47
+ "${MOON}/onnx/vision_encoder_q4.onnx"
48
+ curl -fsSL -o vision/embed_tokens_q4.onnx \
49
+ "${MOON}/onnx/embed_tokens_q4.onnx"
50
+ curl -fsSL -o vision/decoder_model_merged_q4.onnx \
51
+ "${MOON}/onnx/decoder_model_merged_q4.onnx"
52
+ curl -fsSL -o vision/tokenizer.json \
53
+ "${MOON}/tokenizer.json"
54
+
55
+ # --- Piper voices ---
56
+ echo "=== Piper voices ==="
57
+ PIPER="https://huggingface.co/rhasspy/piper-voices/resolve/main"
58
+ for VOICE in en_US-amy-medium en_US-ryan-medium en_US-lessac-medium en_GB-alan-medium; do
59
+ LANG="${VOICE%%-*}"
60
+ LANG2="${LANG%%_*}"
61
+ QUALITY="${VOICE##*-}"
62
+ TMP="${VOICE#${LANG}-}"
63
+ NAME="${TMP%-${QUALITY}}"
64
+ for EXT in onnx onnx.json; do
65
+ curl -fsSL -o "piper/${VOICE}.${EXT}" \
66
+ "${PIPER}/${LANG2}/${LANG}/${NAME}/${QUALITY}/${VOICE}.${EXT}"
67
+ done
68
+ done
69
+
70
+ echo "=== Done downloading ==="
71
+ ls -lhR .
hubert/hubert.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eedf77687d51ff43bc345874c817d3af116423c2383fc9fc3e965faa57f1a70a
3
+ size 378346471
hubert/hubert_base.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f54b40fd2802423a5643779c4861af1e9ee9c1564dc9d32f54f20b5ffba7db96
3
+ size 189507909
piper/en_GB-alan-medium.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a309668932205e762801f1efc2736cd4b0120329622adf62be09e56339d3330
3
+ size 63201294
piper/en_GB-alan-medium.onnx.json ADDED
@@ -0,0 +1,493 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "audio": {
3
+ "sample_rate": 22050,
4
+ "quality": "medium"
5
+ },
6
+ "espeak": {
7
+ "voice": "en-gb-x-rp"
8
+ },
9
+ "inference": {
10
+ "noise_scale": 0.667,
11
+ "length_scale": 1,
12
+ "noise_w": 0.8
13
+ },
14
+ "phoneme_type": "espeak",
15
+ "phoneme_map": {},
16
+ "phoneme_id_map": {
17
+ "_": [
18
+ 0
19
+ ],
20
+ "^": [
21
+ 1
22
+ ],
23
+ "$": [
24
+ 2
25
+ ],
26
+ " ": [
27
+ 3
28
+ ],
29
+ "!": [
30
+ 4
31
+ ],
32
+ "'": [
33
+ 5
34
+ ],
35
+ "(": [
36
+ 6
37
+ ],
38
+ ")": [
39
+ 7
40
+ ],
41
+ ",": [
42
+ 8
43
+ ],
44
+ "-": [
45
+ 9
46
+ ],
47
+ ".": [
48
+ 10
49
+ ],
50
+ ":": [
51
+ 11
52
+ ],
53
+ ";": [
54
+ 12
55
+ ],
56
+ "?": [
57
+ 13
58
+ ],
59
+ "a": [
60
+ 14
61
+ ],
62
+ "b": [
63
+ 15
64
+ ],
65
+ "c": [
66
+ 16
67
+ ],
68
+ "d": [
69
+ 17
70
+ ],
71
+ "e": [
72
+ 18
73
+ ],
74
+ "f": [
75
+ 19
76
+ ],
77
+ "h": [
78
+ 20
79
+ ],
80
+ "i": [
81
+ 21
82
+ ],
83
+ "j": [
84
+ 22
85
+ ],
86
+ "k": [
87
+ 23
88
+ ],
89
+ "l": [
90
+ 24
91
+ ],
92
+ "m": [
93
+ 25
94
+ ],
95
+ "n": [
96
+ 26
97
+ ],
98
+ "o": [
99
+ 27
100
+ ],
101
+ "p": [
102
+ 28
103
+ ],
104
+ "q": [
105
+ 29
106
+ ],
107
+ "r": [
108
+ 30
109
+ ],
110
+ "s": [
111
+ 31
112
+ ],
113
+ "t": [
114
+ 32
115
+ ],
116
+ "u": [
117
+ 33
118
+ ],
119
+ "v": [
120
+ 34
121
+ ],
122
+ "w": [
123
+ 35
124
+ ],
125
+ "x": [
126
+ 36
127
+ ],
128
+ "y": [
129
+ 37
130
+ ],
131
+ "z": [
132
+ 38
133
+ ],
134
+ "æ": [
135
+ 39
136
+ ],
137
+ "ç": [
138
+ 40
139
+ ],
140
+ "ð": [
141
+ 41
142
+ ],
143
+ "ø": [
144
+ 42
145
+ ],
146
+ "ħ": [
147
+ 43
148
+ ],
149
+ "ŋ": [
150
+ 44
151
+ ],
152
+ "œ": [
153
+ 45
154
+ ],
155
+ "ǀ": [
156
+ 46
157
+ ],
158
+ "ǁ": [
159
+ 47
160
+ ],
161
+ "ǂ": [
162
+ 48
163
+ ],
164
+ "ǃ": [
165
+ 49
166
+ ],
167
+ "ɐ": [
168
+ 50
169
+ ],
170
+ "ɑ": [
171
+ 51
172
+ ],
173
+ "ɒ": [
174
+ 52
175
+ ],
176
+ "ɓ": [
177
+ 53
178
+ ],
179
+ "ɔ": [
180
+ 54
181
+ ],
182
+ "ɕ": [
183
+ 55
184
+ ],
185
+ "ɖ": [
186
+ 56
187
+ ],
188
+ "ɗ": [
189
+ 57
190
+ ],
191
+ "ɘ": [
192
+ 58
193
+ ],
194
+ "ə": [
195
+ 59
196
+ ],
197
+ "ɚ": [
198
+ 60
199
+ ],
200
+ "ɛ": [
201
+ 61
202
+ ],
203
+ "ɜ": [
204
+ 62
205
+ ],
206
+ "ɞ": [
207
+ 63
208
+ ],
209
+ "ɟ": [
210
+ 64
211
+ ],
212
+ "ɠ": [
213
+ 65
214
+ ],
215
+ "ɡ": [
216
+ 66
217
+ ],
218
+ "ɢ": [
219
+ 67
220
+ ],
221
+ "ɣ": [
222
+ 68
223
+ ],
224
+ "ɤ": [
225
+ 69
226
+ ],
227
+ "ɥ": [
228
+ 70
229
+ ],
230
+ "ɦ": [
231
+ 71
232
+ ],
233
+ "ɧ": [
234
+ 72
235
+ ],
236
+ "ɨ": [
237
+ 73
238
+ ],
239
+ "ɪ": [
240
+ 74
241
+ ],
242
+ "ɫ": [
243
+ 75
244
+ ],
245
+ "ɬ": [
246
+ 76
247
+ ],
248
+ "ɭ": [
249
+ 77
250
+ ],
251
+ "ɮ": [
252
+ 78
253
+ ],
254
+ "ɯ": [
255
+ 79
256
+ ],
257
+ "ɰ": [
258
+ 80
259
+ ],
260
+ "ɱ": [
261
+ 81
262
+ ],
263
+ "ɲ": [
264
+ 82
265
+ ],
266
+ "ɳ": [
267
+ 83
268
+ ],
269
+ "ɴ": [
270
+ 84
271
+ ],
272
+ "ɵ": [
273
+ 85
274
+ ],
275
+ "ɶ": [
276
+ 86
277
+ ],
278
+ "ɸ": [
279
+ 87
280
+ ],
281
+ "ɹ": [
282
+ 88
283
+ ],
284
+ "ɺ": [
285
+ 89
286
+ ],
287
+ "ɻ": [
288
+ 90
289
+ ],
290
+ "ɽ": [
291
+ 91
292
+ ],
293
+ "ɾ": [
294
+ 92
295
+ ],
296
+ "ʀ": [
297
+ 93
298
+ ],
299
+ "ʁ": [
300
+ 94
301
+ ],
302
+ "ʂ": [
303
+ 95
304
+ ],
305
+ "ʃ": [
306
+ 96
307
+ ],
308
+ "ʄ": [
309
+ 97
310
+ ],
311
+ "ʈ": [
312
+ 98
313
+ ],
314
+ "ʉ": [
315
+ 99
316
+ ],
317
+ "ʊ": [
318
+ 100
319
+ ],
320
+ "ʋ": [
321
+ 101
322
+ ],
323
+ "ʌ": [
324
+ 102
325
+ ],
326
+ "ʍ": [
327
+ 103
328
+ ],
329
+ "ʎ": [
330
+ 104
331
+ ],
332
+ "ʏ": [
333
+ 105
334
+ ],
335
+ "ʐ": [
336
+ 106
337
+ ],
338
+ "ʑ": [
339
+ 107
340
+ ],
341
+ "ʒ": [
342
+ 108
343
+ ],
344
+ "ʔ": [
345
+ 109
346
+ ],
347
+ "ʕ": [
348
+ 110
349
+ ],
350
+ "ʘ": [
351
+ 111
352
+ ],
353
+ "ʙ": [
354
+ 112
355
+ ],
356
+ "ʛ": [
357
+ 113
358
+ ],
359
+ "ʜ": [
360
+ 114
361
+ ],
362
+ "ʝ": [
363
+ 115
364
+ ],
365
+ "ʟ": [
366
+ 116
367
+ ],
368
+ "ʡ": [
369
+ 117
370
+ ],
371
+ "ʢ": [
372
+ 118
373
+ ],
374
+ "ʲ": [
375
+ 119
376
+ ],
377
+ "ˈ": [
378
+ 120
379
+ ],
380
+ "ˌ": [
381
+ 121
382
+ ],
383
+ "ː": [
384
+ 122
385
+ ],
386
+ "ˑ": [
387
+ 123
388
+ ],
389
+ "˞": [
390
+ 124
391
+ ],
392
+ "β": [
393
+ 125
394
+ ],
395
+ "θ": [
396
+ 126
397
+ ],
398
+ "χ": [
399
+ 127
400
+ ],
401
+ "ᵻ": [
402
+ 128
403
+ ],
404
+ "ⱱ": [
405
+ 129
406
+ ],
407
+ "0": [
408
+ 130
409
+ ],
410
+ "1": [
411
+ 131
412
+ ],
413
+ "2": [
414
+ 132
415
+ ],
416
+ "3": [
417
+ 133
418
+ ],
419
+ "4": [
420
+ 134
421
+ ],
422
+ "5": [
423
+ 135
424
+ ],
425
+ "6": [
426
+ 136
427
+ ],
428
+ "7": [
429
+ 137
430
+ ],
431
+ "8": [
432
+ 138
433
+ ],
434
+ "9": [
435
+ 139
436
+ ],
437
+ "̧": [
438
+ 140
439
+ ],
440
+ "̃": [
441
+ 141
442
+ ],
443
+ "̪": [
444
+ 142
445
+ ],
446
+ "̯": [
447
+ 143
448
+ ],
449
+ "̩": [
450
+ 144
451
+ ],
452
+ "ʰ": [
453
+ 145
454
+ ],
455
+ "ˤ": [
456
+ 146
457
+ ],
458
+ "ε": [
459
+ 147
460
+ ],
461
+ "↓": [
462
+ 148
463
+ ],
464
+ "#": [
465
+ 149
466
+ ],
467
+ "\"": [
468
+ 150
469
+ ],
470
+ "↑": [
471
+ 151
472
+ ],
473
+ "̺": [
474
+ 152
475
+ ],
476
+ "̻": [
477
+ 153
478
+ ]
479
+ },
480
+ "num_symbols": 256,
481
+ "num_speakers": 1,
482
+ "speaker_id_map": {},
483
+ "piper_version": "1.0.0",
484
+ "language": {
485
+ "code": "en_GB",
486
+ "family": "en",
487
+ "region": "GB",
488
+ "name_native": "English",
489
+ "name_english": "English",
490
+ "country_english": "Great Britain"
491
+ },
492
+ "dataset": "alan"
493
+ }
piper/en_US-amy-medium.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3a6e47b57b8c7fbe6a0ce2518161a50f59a9cdd8a50835c02cb02bdd6206c18
3
+ size 63201294
piper/en_US-amy-medium.onnx.json ADDED
@@ -0,0 +1,493 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "audio": {
3
+ "sample_rate": 22050,
4
+ "quality": "medium"
5
+ },
6
+ "espeak": {
7
+ "voice": "en-us"
8
+ },
9
+ "inference": {
10
+ "noise_scale": 0.667,
11
+ "length_scale": 1,
12
+ "noise_w": 0.8
13
+ },
14
+ "phoneme_type": "espeak",
15
+ "phoneme_map": {},
16
+ "phoneme_id_map": {
17
+ "_": [
18
+ 0
19
+ ],
20
+ "^": [
21
+ 1
22
+ ],
23
+ "$": [
24
+ 2
25
+ ],
26
+ " ": [
27
+ 3
28
+ ],
29
+ "!": [
30
+ 4
31
+ ],
32
+ "'": [
33
+ 5
34
+ ],
35
+ "(": [
36
+ 6
37
+ ],
38
+ ")": [
39
+ 7
40
+ ],
41
+ ",": [
42
+ 8
43
+ ],
44
+ "-": [
45
+ 9
46
+ ],
47
+ ".": [
48
+ 10
49
+ ],
50
+ ":": [
51
+ 11
52
+ ],
53
+ ";": [
54
+ 12
55
+ ],
56
+ "?": [
57
+ 13
58
+ ],
59
+ "a": [
60
+ 14
61
+ ],
62
+ "b": [
63
+ 15
64
+ ],
65
+ "c": [
66
+ 16
67
+ ],
68
+ "d": [
69
+ 17
70
+ ],
71
+ "e": [
72
+ 18
73
+ ],
74
+ "f": [
75
+ 19
76
+ ],
77
+ "h": [
78
+ 20
79
+ ],
80
+ "i": [
81
+ 21
82
+ ],
83
+ "j": [
84
+ 22
85
+ ],
86
+ "k": [
87
+ 23
88
+ ],
89
+ "l": [
90
+ 24
91
+ ],
92
+ "m": [
93
+ 25
94
+ ],
95
+ "n": [
96
+ 26
97
+ ],
98
+ "o": [
99
+ 27
100
+ ],
101
+ "p": [
102
+ 28
103
+ ],
104
+ "q": [
105
+ 29
106
+ ],
107
+ "r": [
108
+ 30
109
+ ],
110
+ "s": [
111
+ 31
112
+ ],
113
+ "t": [
114
+ 32
115
+ ],
116
+ "u": [
117
+ 33
118
+ ],
119
+ "v": [
120
+ 34
121
+ ],
122
+ "w": [
123
+ 35
124
+ ],
125
+ "x": [
126
+ 36
127
+ ],
128
+ "y": [
129
+ 37
130
+ ],
131
+ "z": [
132
+ 38
133
+ ],
134
+ "æ": [
135
+ 39
136
+ ],
137
+ "ç": [
138
+ 40
139
+ ],
140
+ "ð": [
141
+ 41
142
+ ],
143
+ "ø": [
144
+ 42
145
+ ],
146
+ "ħ": [
147
+ 43
148
+ ],
149
+ "ŋ": [
150
+ 44
151
+ ],
152
+ "œ": [
153
+ 45
154
+ ],
155
+ "ǀ": [
156
+ 46
157
+ ],
158
+ "ǁ": [
159
+ 47
160
+ ],
161
+ "ǂ": [
162
+ 48
163
+ ],
164
+ "ǃ": [
165
+ 49
166
+ ],
167
+ "ɐ": [
168
+ 50
169
+ ],
170
+ "ɑ": [
171
+ 51
172
+ ],
173
+ "ɒ": [
174
+ 52
175
+ ],
176
+ "ɓ": [
177
+ 53
178
+ ],
179
+ "ɔ": [
180
+ 54
181
+ ],
182
+ "ɕ": [
183
+ 55
184
+ ],
185
+ "ɖ": [
186
+ 56
187
+ ],
188
+ "ɗ": [
189
+ 57
190
+ ],
191
+ "ɘ": [
192
+ 58
193
+ ],
194
+ "ə": [
195
+ 59
196
+ ],
197
+ "ɚ": [
198
+ 60
199
+ ],
200
+ "ɛ": [
201
+ 61
202
+ ],
203
+ "ɜ": [
204
+ 62
205
+ ],
206
+ "ɞ": [
207
+ 63
208
+ ],
209
+ "ɟ": [
210
+ 64
211
+ ],
212
+ "ɠ": [
213
+ 65
214
+ ],
215
+ "ɡ": [
216
+ 66
217
+ ],
218
+ "ɢ": [
219
+ 67
220
+ ],
221
+ "ɣ": [
222
+ 68
223
+ ],
224
+ "ɤ": [
225
+ 69
226
+ ],
227
+ "ɥ": [
228
+ 70
229
+ ],
230
+ "ɦ": [
231
+ 71
232
+ ],
233
+ "ɧ": [
234
+ 72
235
+ ],
236
+ "ɨ": [
237
+ 73
238
+ ],
239
+ "ɪ": [
240
+ 74
241
+ ],
242
+ "ɫ": [
243
+ 75
244
+ ],
245
+ "ɬ": [
246
+ 76
247
+ ],
248
+ "ɭ": [
249
+ 77
250
+ ],
251
+ "ɮ": [
252
+ 78
253
+ ],
254
+ "ɯ": [
255
+ 79
256
+ ],
257
+ "ɰ": [
258
+ 80
259
+ ],
260
+ "ɱ": [
261
+ 81
262
+ ],
263
+ "ɲ": [
264
+ 82
265
+ ],
266
+ "ɳ": [
267
+ 83
268
+ ],
269
+ "ɴ": [
270
+ 84
271
+ ],
272
+ "ɵ": [
273
+ 85
274
+ ],
275
+ "ɶ": [
276
+ 86
277
+ ],
278
+ "ɸ": [
279
+ 87
280
+ ],
281
+ "ɹ": [
282
+ 88
283
+ ],
284
+ "ɺ": [
285
+ 89
286
+ ],
287
+ "ɻ": [
288
+ 90
289
+ ],
290
+ "ɽ": [
291
+ 91
292
+ ],
293
+ "ɾ": [
294
+ 92
295
+ ],
296
+ "ʀ": [
297
+ 93
298
+ ],
299
+ "ʁ": [
300
+ 94
301
+ ],
302
+ "ʂ": [
303
+ 95
304
+ ],
305
+ "ʃ": [
306
+ 96
307
+ ],
308
+ "ʄ": [
309
+ 97
310
+ ],
311
+ "ʈ": [
312
+ 98
313
+ ],
314
+ "ʉ": [
315
+ 99
316
+ ],
317
+ "ʊ": [
318
+ 100
319
+ ],
320
+ "ʋ": [
321
+ 101
322
+ ],
323
+ "ʌ": [
324
+ 102
325
+ ],
326
+ "ʍ": [
327
+ 103
328
+ ],
329
+ "ʎ": [
330
+ 104
331
+ ],
332
+ "ʏ": [
333
+ 105
334
+ ],
335
+ "ʐ": [
336
+ 106
337
+ ],
338
+ "ʑ": [
339
+ 107
340
+ ],
341
+ "ʒ": [
342
+ 108
343
+ ],
344
+ "ʔ": [
345
+ 109
346
+ ],
347
+ "ʕ": [
348
+ 110
349
+ ],
350
+ "ʘ": [
351
+ 111
352
+ ],
353
+ "ʙ": [
354
+ 112
355
+ ],
356
+ "ʛ": [
357
+ 113
358
+ ],
359
+ "ʜ": [
360
+ 114
361
+ ],
362
+ "ʝ": [
363
+ 115
364
+ ],
365
+ "ʟ": [
366
+ 116
367
+ ],
368
+ "ʡ": [
369
+ 117
370
+ ],
371
+ "ʢ": [
372
+ 118
373
+ ],
374
+ "ʲ": [
375
+ 119
376
+ ],
377
+ "ˈ": [
378
+ 120
379
+ ],
380
+ "ˌ": [
381
+ 121
382
+ ],
383
+ "ː": [
384
+ 122
385
+ ],
386
+ "ˑ": [
387
+ 123
388
+ ],
389
+ "˞": [
390
+ 124
391
+ ],
392
+ "β": [
393
+ 125
394
+ ],
395
+ "θ": [
396
+ 126
397
+ ],
398
+ "χ": [
399
+ 127
400
+ ],
401
+ "ᵻ": [
402
+ 128
403
+ ],
404
+ "ⱱ": [
405
+ 129
406
+ ],
407
+ "0": [
408
+ 130
409
+ ],
410
+ "1": [
411
+ 131
412
+ ],
413
+ "2": [
414
+ 132
415
+ ],
416
+ "3": [
417
+ 133
418
+ ],
419
+ "4": [
420
+ 134
421
+ ],
422
+ "5": [
423
+ 135
424
+ ],
425
+ "6": [
426
+ 136
427
+ ],
428
+ "7": [
429
+ 137
430
+ ],
431
+ "8": [
432
+ 138
433
+ ],
434
+ "9": [
435
+ 139
436
+ ],
437
+ "̧": [
438
+ 140
439
+ ],
440
+ "̃": [
441
+ 141
442
+ ],
443
+ "̪": [
444
+ 142
445
+ ],
446
+ "̯": [
447
+ 143
448
+ ],
449
+ "̩": [
450
+ 144
451
+ ],
452
+ "ʰ": [
453
+ 145
454
+ ],
455
+ "ˤ": [
456
+ 146
457
+ ],
458
+ "ε": [
459
+ 147
460
+ ],
461
+ "↓": [
462
+ 148
463
+ ],
464
+ "#": [
465
+ 149
466
+ ],
467
+ "\"": [
468
+ 150
469
+ ],
470
+ "↑": [
471
+ 151
472
+ ],
473
+ "̺": [
474
+ 152
475
+ ],
476
+ "̻": [
477
+ 153
478
+ ]
479
+ },
480
+ "num_symbols": 256,
481
+ "num_speakers": 1,
482
+ "speaker_id_map": {},
483
+ "piper_version": "1.0.0",
484
+ "language": {
485
+ "code": "en_US",
486
+ "family": "en",
487
+ "region": "US",
488
+ "name_native": "English",
489
+ "name_english": "English",
490
+ "country_english": "United States"
491
+ },
492
+ "dataset": "amy"
493
+ }
piper/en_US-lessac-medium.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5efe09e69902187827af646e1a6e9d269dee769f9877d17b16b1b46eeaaf019f
3
+ size 63201294
piper/en_US-lessac-medium.onnx.json ADDED
@@ -0,0 +1,493 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "audio": {
3
+ "sample_rate": 22050,
4
+ "quality": "medium"
5
+ },
6
+ "espeak": {
7
+ "voice": "en-us"
8
+ },
9
+ "inference": {
10
+ "noise_scale": 0.667,
11
+ "length_scale": 1,
12
+ "noise_w": 0.8
13
+ },
14
+ "phoneme_type": "espeak",
15
+ "phoneme_map": {},
16
+ "phoneme_id_map": {
17
+ "_": [
18
+ 0
19
+ ],
20
+ "^": [
21
+ 1
22
+ ],
23
+ "$": [
24
+ 2
25
+ ],
26
+ " ": [
27
+ 3
28
+ ],
29
+ "!": [
30
+ 4
31
+ ],
32
+ "'": [
33
+ 5
34
+ ],
35
+ "(": [
36
+ 6
37
+ ],
38
+ ")": [
39
+ 7
40
+ ],
41
+ ",": [
42
+ 8
43
+ ],
44
+ "-": [
45
+ 9
46
+ ],
47
+ ".": [
48
+ 10
49
+ ],
50
+ ":": [
51
+ 11
52
+ ],
53
+ ";": [
54
+ 12
55
+ ],
56
+ "?": [
57
+ 13
58
+ ],
59
+ "a": [
60
+ 14
61
+ ],
62
+ "b": [
63
+ 15
64
+ ],
65
+ "c": [
66
+ 16
67
+ ],
68
+ "d": [
69
+ 17
70
+ ],
71
+ "e": [
72
+ 18
73
+ ],
74
+ "f": [
75
+ 19
76
+ ],
77
+ "h": [
78
+ 20
79
+ ],
80
+ "i": [
81
+ 21
82
+ ],
83
+ "j": [
84
+ 22
85
+ ],
86
+ "k": [
87
+ 23
88
+ ],
89
+ "l": [
90
+ 24
91
+ ],
92
+ "m": [
93
+ 25
94
+ ],
95
+ "n": [
96
+ 26
97
+ ],
98
+ "o": [
99
+ 27
100
+ ],
101
+ "p": [
102
+ 28
103
+ ],
104
+ "q": [
105
+ 29
106
+ ],
107
+ "r": [
108
+ 30
109
+ ],
110
+ "s": [
111
+ 31
112
+ ],
113
+ "t": [
114
+ 32
115
+ ],
116
+ "u": [
117
+ 33
118
+ ],
119
+ "v": [
120
+ 34
121
+ ],
122
+ "w": [
123
+ 35
124
+ ],
125
+ "x": [
126
+ 36
127
+ ],
128
+ "y": [
129
+ 37
130
+ ],
131
+ "z": [
132
+ 38
133
+ ],
134
+ "æ": [
135
+ 39
136
+ ],
137
+ "ç": [
138
+ 40
139
+ ],
140
+ "ð": [
141
+ 41
142
+ ],
143
+ "ø": [
144
+ 42
145
+ ],
146
+ "ħ": [
147
+ 43
148
+ ],
149
+ "ŋ": [
150
+ 44
151
+ ],
152
+ "œ": [
153
+ 45
154
+ ],
155
+ "ǀ": [
156
+ 46
157
+ ],
158
+ "ǁ": [
159
+ 47
160
+ ],
161
+ "ǂ": [
162
+ 48
163
+ ],
164
+ "ǃ": [
165
+ 49
166
+ ],
167
+ "ɐ": [
168
+ 50
169
+ ],
170
+ "ɑ": [
171
+ 51
172
+ ],
173
+ "ɒ": [
174
+ 52
175
+ ],
176
+ "ɓ": [
177
+ 53
178
+ ],
179
+ "ɔ": [
180
+ 54
181
+ ],
182
+ "ɕ": [
183
+ 55
184
+ ],
185
+ "ɖ": [
186
+ 56
187
+ ],
188
+ "ɗ": [
189
+ 57
190
+ ],
191
+ "ɘ": [
192
+ 58
193
+ ],
194
+ "ə": [
195
+ 59
196
+ ],
197
+ "ɚ": [
198
+ 60
199
+ ],
200
+ "ɛ": [
201
+ 61
202
+ ],
203
+ "ɜ": [
204
+ 62
205
+ ],
206
+ "ɞ": [
207
+ 63
208
+ ],
209
+ "ɟ": [
210
+ 64
211
+ ],
212
+ "ɠ": [
213
+ 65
214
+ ],
215
+ "ɡ": [
216
+ 66
217
+ ],
218
+ "ɢ": [
219
+ 67
220
+ ],
221
+ "ɣ": [
222
+ 68
223
+ ],
224
+ "ɤ": [
225
+ 69
226
+ ],
227
+ "ɥ": [
228
+ 70
229
+ ],
230
+ "ɦ": [
231
+ 71
232
+ ],
233
+ "ɧ": [
234
+ 72
235
+ ],
236
+ "ɨ": [
237
+ 73
238
+ ],
239
+ "ɪ": [
240
+ 74
241
+ ],
242
+ "ɫ": [
243
+ 75
244
+ ],
245
+ "ɬ": [
246
+ 76
247
+ ],
248
+ "ɭ": [
249
+ 77
250
+ ],
251
+ "ɮ": [
252
+ 78
253
+ ],
254
+ "ɯ": [
255
+ 79
256
+ ],
257
+ "ɰ": [
258
+ 80
259
+ ],
260
+ "ɱ": [
261
+ 81
262
+ ],
263
+ "ɲ": [
264
+ 82
265
+ ],
266
+ "ɳ": [
267
+ 83
268
+ ],
269
+ "ɴ": [
270
+ 84
271
+ ],
272
+ "ɵ": [
273
+ 85
274
+ ],
275
+ "ɶ": [
276
+ 86
277
+ ],
278
+ "ɸ": [
279
+ 87
280
+ ],
281
+ "ɹ": [
282
+ 88
283
+ ],
284
+ "ɺ": [
285
+ 89
286
+ ],
287
+ "ɻ": [
288
+ 90
289
+ ],
290
+ "ɽ": [
291
+ 91
292
+ ],
293
+ "ɾ": [
294
+ 92
295
+ ],
296
+ "ʀ": [
297
+ 93
298
+ ],
299
+ "ʁ": [
300
+ 94
301
+ ],
302
+ "ʂ": [
303
+ 95
304
+ ],
305
+ "ʃ": [
306
+ 96
307
+ ],
308
+ "ʄ": [
309
+ 97
310
+ ],
311
+ "ʈ": [
312
+ 98
313
+ ],
314
+ "ʉ": [
315
+ 99
316
+ ],
317
+ "ʊ": [
318
+ 100
319
+ ],
320
+ "ʋ": [
321
+ 101
322
+ ],
323
+ "ʌ": [
324
+ 102
325
+ ],
326
+ "ʍ": [
327
+ 103
328
+ ],
329
+ "ʎ": [
330
+ 104
331
+ ],
332
+ "ʏ": [
333
+ 105
334
+ ],
335
+ "ʐ": [
336
+ 106
337
+ ],
338
+ "ʑ": [
339
+ 107
340
+ ],
341
+ "ʒ": [
342
+ 108
343
+ ],
344
+ "ʔ": [
345
+ 109
346
+ ],
347
+ "ʕ": [
348
+ 110
349
+ ],
350
+ "ʘ": [
351
+ 111
352
+ ],
353
+ "ʙ": [
354
+ 112
355
+ ],
356
+ "ʛ": [
357
+ 113
358
+ ],
359
+ "ʜ": [
360
+ 114
361
+ ],
362
+ "ʝ": [
363
+ 115
364
+ ],
365
+ "ʟ": [
366
+ 116
367
+ ],
368
+ "ʡ": [
369
+ 117
370
+ ],
371
+ "ʢ": [
372
+ 118
373
+ ],
374
+ "ʲ": [
375
+ 119
376
+ ],
377
+ "ˈ": [
378
+ 120
379
+ ],
380
+ "ˌ": [
381
+ 121
382
+ ],
383
+ "ː": [
384
+ 122
385
+ ],
386
+ "ˑ": [
387
+ 123
388
+ ],
389
+ "˞": [
390
+ 124
391
+ ],
392
+ "β": [
393
+ 125
394
+ ],
395
+ "θ": [
396
+ 126
397
+ ],
398
+ "χ": [
399
+ 127
400
+ ],
401
+ "ᵻ": [
402
+ 128
403
+ ],
404
+ "ⱱ": [
405
+ 129
406
+ ],
407
+ "0": [
408
+ 130
409
+ ],
410
+ "1": [
411
+ 131
412
+ ],
413
+ "2": [
414
+ 132
415
+ ],
416
+ "3": [
417
+ 133
418
+ ],
419
+ "4": [
420
+ 134
421
+ ],
422
+ "5": [
423
+ 135
424
+ ],
425
+ "6": [
426
+ 136
427
+ ],
428
+ "7": [
429
+ 137
430
+ ],
431
+ "8": [
432
+ 138
433
+ ],
434
+ "9": [
435
+ 139
436
+ ],
437
+ "̧": [
438
+ 140
439
+ ],
440
+ "̃": [
441
+ 141
442
+ ],
443
+ "̪": [
444
+ 142
445
+ ],
446
+ "̯": [
447
+ 143
448
+ ],
449
+ "̩": [
450
+ 144
451
+ ],
452
+ "ʰ": [
453
+ 145
454
+ ],
455
+ "ˤ": [
456
+ 146
457
+ ],
458
+ "ε": [
459
+ 147
460
+ ],
461
+ "↓": [
462
+ 148
463
+ ],
464
+ "#": [
465
+ 149
466
+ ],
467
+ "\"": [
468
+ 150
469
+ ],
470
+ "↑": [
471
+ 151
472
+ ],
473
+ "̺": [
474
+ 152
475
+ ],
476
+ "̻": [
477
+ 153
478
+ ]
479
+ },
480
+ "num_symbols": 256,
481
+ "num_speakers": 1,
482
+ "speaker_id_map": {},
483
+ "piper_version": "1.0.0",
484
+ "language": {
485
+ "code": "en_US",
486
+ "family": "en",
487
+ "region": "US",
488
+ "name_native": "English",
489
+ "name_english": "English",
490
+ "country_english": "United States"
491
+ },
492
+ "dataset": "lessac"
493
+ }
piper/en_US-ryan-medium.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abf4c274862564ed647ba0d2c47f8ee7c9b717d27bdad9219100eb310db4047a
3
+ size 63201294
piper/en_US-ryan-medium.onnx.json ADDED
@@ -0,0 +1,493 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "audio": {
3
+ "sample_rate": 22050,
4
+ "quality": "medium"
5
+ },
6
+ "espeak": {
7
+ "voice": "en-us"
8
+ },
9
+ "inference": {
10
+ "noise_scale": 0.667,
11
+ "length_scale": 1,
12
+ "noise_w": 0.8
13
+ },
14
+ "phoneme_type": "espeak",
15
+ "phoneme_map": {},
16
+ "phoneme_id_map": {
17
+ "_": [
18
+ 0
19
+ ],
20
+ "^": [
21
+ 1
22
+ ],
23
+ "$": [
24
+ 2
25
+ ],
26
+ " ": [
27
+ 3
28
+ ],
29
+ "!": [
30
+ 4
31
+ ],
32
+ "'": [
33
+ 5
34
+ ],
35
+ "(": [
36
+ 6
37
+ ],
38
+ ")": [
39
+ 7
40
+ ],
41
+ ",": [
42
+ 8
43
+ ],
44
+ "-": [
45
+ 9
46
+ ],
47
+ ".": [
48
+ 10
49
+ ],
50
+ ":": [
51
+ 11
52
+ ],
53
+ ";": [
54
+ 12
55
+ ],
56
+ "?": [
57
+ 13
58
+ ],
59
+ "a": [
60
+ 14
61
+ ],
62
+ "b": [
63
+ 15
64
+ ],
65
+ "c": [
66
+ 16
67
+ ],
68
+ "d": [
69
+ 17
70
+ ],
71
+ "e": [
72
+ 18
73
+ ],
74
+ "f": [
75
+ 19
76
+ ],
77
+ "h": [
78
+ 20
79
+ ],
80
+ "i": [
81
+ 21
82
+ ],
83
+ "j": [
84
+ 22
85
+ ],
86
+ "k": [
87
+ 23
88
+ ],
89
+ "l": [
90
+ 24
91
+ ],
92
+ "m": [
93
+ 25
94
+ ],
95
+ "n": [
96
+ 26
97
+ ],
98
+ "o": [
99
+ 27
100
+ ],
101
+ "p": [
102
+ 28
103
+ ],
104
+ "q": [
105
+ 29
106
+ ],
107
+ "r": [
108
+ 30
109
+ ],
110
+ "s": [
111
+ 31
112
+ ],
113
+ "t": [
114
+ 32
115
+ ],
116
+ "u": [
117
+ 33
118
+ ],
119
+ "v": [
120
+ 34
121
+ ],
122
+ "w": [
123
+ 35
124
+ ],
125
+ "x": [
126
+ 36
127
+ ],
128
+ "y": [
129
+ 37
130
+ ],
131
+ "z": [
132
+ 38
133
+ ],
134
+ "æ": [
135
+ 39
136
+ ],
137
+ "ç": [
138
+ 40
139
+ ],
140
+ "ð": [
141
+ 41
142
+ ],
143
+ "ø": [
144
+ 42
145
+ ],
146
+ "ħ": [
147
+ 43
148
+ ],
149
+ "ŋ": [
150
+ 44
151
+ ],
152
+ "œ": [
153
+ 45
154
+ ],
155
+ "ǀ": [
156
+ 46
157
+ ],
158
+ "ǁ": [
159
+ 47
160
+ ],
161
+ "ǂ": [
162
+ 48
163
+ ],
164
+ "ǃ": [
165
+ 49
166
+ ],
167
+ "ɐ": [
168
+ 50
169
+ ],
170
+ "ɑ": [
171
+ 51
172
+ ],
173
+ "ɒ": [
174
+ 52
175
+ ],
176
+ "ɓ": [
177
+ 53
178
+ ],
179
+ "ɔ": [
180
+ 54
181
+ ],
182
+ "ɕ": [
183
+ 55
184
+ ],
185
+ "ɖ": [
186
+ 56
187
+ ],
188
+ "ɗ": [
189
+ 57
190
+ ],
191
+ "ɘ": [
192
+ 58
193
+ ],
194
+ "ə": [
195
+ 59
196
+ ],
197
+ "ɚ": [
198
+ 60
199
+ ],
200
+ "ɛ": [
201
+ 61
202
+ ],
203
+ "ɜ": [
204
+ 62
205
+ ],
206
+ "ɞ": [
207
+ 63
208
+ ],
209
+ "ɟ": [
210
+ 64
211
+ ],
212
+ "ɠ": [
213
+ 65
214
+ ],
215
+ "ɡ": [
216
+ 66
217
+ ],
218
+ "ɢ": [
219
+ 67
220
+ ],
221
+ "ɣ": [
222
+ 68
223
+ ],
224
+ "ɤ": [
225
+ 69
226
+ ],
227
+ "ɥ": [
228
+ 70
229
+ ],
230
+ "ɦ": [
231
+ 71
232
+ ],
233
+ "ɧ": [
234
+ 72
235
+ ],
236
+ "ɨ": [
237
+ 73
238
+ ],
239
+ "ɪ": [
240
+ 74
241
+ ],
242
+ "ɫ": [
243
+ 75
244
+ ],
245
+ "ɬ": [
246
+ 76
247
+ ],
248
+ "ɭ": [
249
+ 77
250
+ ],
251
+ "ɮ": [
252
+ 78
253
+ ],
254
+ "ɯ": [
255
+ 79
256
+ ],
257
+ "ɰ": [
258
+ 80
259
+ ],
260
+ "ɱ": [
261
+ 81
262
+ ],
263
+ "ɲ": [
264
+ 82
265
+ ],
266
+ "ɳ": [
267
+ 83
268
+ ],
269
+ "ɴ": [
270
+ 84
271
+ ],
272
+ "ɵ": [
273
+ 85
274
+ ],
275
+ "ɶ": [
276
+ 86
277
+ ],
278
+ "ɸ": [
279
+ 87
280
+ ],
281
+ "ɹ": [
282
+ 88
283
+ ],
284
+ "ɺ": [
285
+ 89
286
+ ],
287
+ "ɻ": [
288
+ 90
289
+ ],
290
+ "ɽ": [
291
+ 91
292
+ ],
293
+ "ɾ": [
294
+ 92
295
+ ],
296
+ "ʀ": [
297
+ 93
298
+ ],
299
+ "ʁ": [
300
+ 94
301
+ ],
302
+ "ʂ": [
303
+ 95
304
+ ],
305
+ "ʃ": [
306
+ 96
307
+ ],
308
+ "ʄ": [
309
+ 97
310
+ ],
311
+ "ʈ": [
312
+ 98
313
+ ],
314
+ "ʉ": [
315
+ 99
316
+ ],
317
+ "ʊ": [
318
+ 100
319
+ ],
320
+ "ʋ": [
321
+ 101
322
+ ],
323
+ "ʌ": [
324
+ 102
325
+ ],
326
+ "ʍ": [
327
+ 103
328
+ ],
329
+ "ʎ": [
330
+ 104
331
+ ],
332
+ "ʏ": [
333
+ 105
334
+ ],
335
+ "ʐ": [
336
+ 106
337
+ ],
338
+ "ʑ": [
339
+ 107
340
+ ],
341
+ "ʒ": [
342
+ 108
343
+ ],
344
+ "ʔ": [
345
+ 109
346
+ ],
347
+ "ʕ": [
348
+ 110
349
+ ],
350
+ "ʘ": [
351
+ 111
352
+ ],
353
+ "ʙ": [
354
+ 112
355
+ ],
356
+ "ʛ": [
357
+ 113
358
+ ],
359
+ "ʜ": [
360
+ 114
361
+ ],
362
+ "ʝ": [
363
+ 115
364
+ ],
365
+ "ʟ": [
366
+ 116
367
+ ],
368
+ "ʡ": [
369
+ 117
370
+ ],
371
+ "ʢ": [
372
+ 118
373
+ ],
374
+ "ʲ": [
375
+ 119
376
+ ],
377
+ "ˈ": [
378
+ 120
379
+ ],
380
+ "ˌ": [
381
+ 121
382
+ ],
383
+ "ː": [
384
+ 122
385
+ ],
386
+ "ˑ": [
387
+ 123
388
+ ],
389
+ "˞": [
390
+ 124
391
+ ],
392
+ "β": [
393
+ 125
394
+ ],
395
+ "θ": [
396
+ 126
397
+ ],
398
+ "χ": [
399
+ 127
400
+ ],
401
+ "ᵻ": [
402
+ 128
403
+ ],
404
+ "ⱱ": [
405
+ 129
406
+ ],
407
+ "0": [
408
+ 130
409
+ ],
410
+ "1": [
411
+ 131
412
+ ],
413
+ "2": [
414
+ 132
415
+ ],
416
+ "3": [
417
+ 133
418
+ ],
419
+ "4": [
420
+ 134
421
+ ],
422
+ "5": [
423
+ 135
424
+ ],
425
+ "6": [
426
+ 136
427
+ ],
428
+ "7": [
429
+ 137
430
+ ],
431
+ "8": [
432
+ 138
433
+ ],
434
+ "9": [
435
+ 139
436
+ ],
437
+ "̧": [
438
+ 140
439
+ ],
440
+ "̃": [
441
+ 141
442
+ ],
443
+ "̪": [
444
+ 142
445
+ ],
446
+ "̯": [
447
+ 143
448
+ ],
449
+ "̩": [
450
+ 144
451
+ ],
452
+ "ʰ": [
453
+ 145
454
+ ],
455
+ "ˤ": [
456
+ 146
457
+ ],
458
+ "ε": [
459
+ 147
460
+ ],
461
+ "↓": [
462
+ 148
463
+ ],
464
+ "#": [
465
+ 149
466
+ ],
467
+ "\"": [
468
+ 150
469
+ ],
470
+ "↑": [
471
+ 151
472
+ ],
473
+ "̺": [
474
+ 152
475
+ ],
476
+ "̻": [
477
+ 153
478
+ ]
479
+ },
480
+ "num_symbols": 256,
481
+ "num_speakers": 1,
482
+ "speaker_id_map": {},
483
+ "piper_version": "1.0.0",
484
+ "language": {
485
+ "code": "en_US",
486
+ "family": "en",
487
+ "region": "US",
488
+ "name_native": "English",
489
+ "name_english": "English",
490
+ "country_english": "United States"
491
+ },
492
+ "dataset": "ryan"
493
+ }
rvc/rmvpe.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5370e71ac80af8b4b7c793d27efd51fd8bf962de3a7ede0766dac0befa3660fd
3
+ size 361688443
separation/Kim_Vocal_2.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce74ef3b6a6024ce44211a07be9cf8bc6d87728cc852a68ab34eb8e58cde9c8b
3
+ size 66759214
vision/decoder_model_merged_q4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c6c986cb277a8dbafb4d437b6e56717fbe3dab7c0d9efceb77cfde48d081273
3
+ size 824343527
vision/embed_tokens_q4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e83c0024e7785c5946ecda27729cdb4d32d5e6b72d75bc58a155f3d7247967ef
3
+ size 419430658
vision/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
vision/vision_encoder_q4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2458ab4ab41f43bb24c2b3aa2d68c34318612a6a628237e6c738ddbf5dc2843
3
+ size 279536385
whisper/ggml-large-v3-turbo-q5_0.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:394221709cd5ad1f40c46e6031ca61bce88931e6e088c188294c6d5a55ffa7e2
3
+ size 574041195
whisper/ggml-tiny.en.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:921e4cf8686fdd993dcd081a5da5b6c365bfde1162e72b08d75ac75289920b1f
3
+ size 77704715