rahul7star commited on
Commit
2ee3ffb
Β·
verified Β·
1 Parent(s): 4b7a169

Chatterbox fine-tuned model + logs

Browse files
Files changed (1) hide show
  1. training.log +55 -58
training.log CHANGED
@@ -1,7 +1,7 @@
1
 
2
  /usr/local/lib/python3.13/site-packages/perth/perth_net/__init__.py:1: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81.
3
  from pkg_resources import resource_filename
4
- 02/07/2026 04:38:10 - INFO - __main__ - Training/evaluation parameters CustomTrainingArguments(
5
  accelerator_config={'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None, 'use_configured_state': False},
6
  adam_beta1=0.9,
7
  adam_beta2=0.999,
@@ -113,114 +113,111 @@ warmup_ratio=None,
113
  warmup_steps=1.0,
114
  weight_decay=0.0,
115
  )
116
- 02/07/2026 04:38:10 - INFO - __main__ - Model parameters ModelArguments(model_name_or_path='ResembleAI/chatterbox', local_model_dir=None, cache_dir=None, freeze_voice_encoder=True, freeze_s3gen=True)
117
- 02/07/2026 04:38:10 - INFO - __main__ - Data parameters DataArguments(language='hi', dataset_dir=None, metadata_file=None, dataset_name='rahul7star/hindi-speech-dataset', dataset_config_name=None, train_split_name='train', eval_split_name='validation', text_column_name='text_scribe', audio_column_name='audio', max_text_len=256, max_speech_len=800, audio_prompt_duration_s=3.0, eval_split_size=0.0002, preprocessing_num_workers=None, ignore_verifications=False)
118
- 02/07/2026 04:38:10 - INFO - __main__ - Loading ChatterboxTTS model...
119
- 02/07/2026 04:38:10 - INFO - __main__ - Loading model from Hugging Face Hub: ResembleAI/chatterbox
120
  /usr/local/lib/python3.13/site-packages/huggingface_hub/utils/_validators.py:202: UserWarning: The `local_dir_use_symlinks` argument is deprecated and ignored in `hf_hub_download`. Downloading to a local directory does not use symlinks anymore.
121
  warnings.warn(
122
- 02/07/2026 04:38:10 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/ResembleAI/chatterbox/resolve/main/ve.safetensors "HTTP/1.1 302 Found"
123
- 02/07/2026 04:38:10 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/models/ResembleAI/chatterbox/xet-read-token/05e904af2b5c7f8e482687a9d7336c5c824467d9 "HTTP/1.1 200 OK"
124
 
125
 
126
  ve.safetensors: 0%| | 0.00/5.70M [00:00<?, ?B/s]
127
- ve.safetensors: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 5.70M/5.70M [00:00<00:00, 29.2MB/s]
128
- 02/07/2026 04:38:10 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/ResembleAI/chatterbox/resolve/main/t3_mtl23ls_v2.safetensors "HTTP/1.1 302 Found"
129
 
130
 
131
  t3_mtl23ls_v2.safetensors: 0%| | 0.00/2.14G [00:00<?, ?B/s]
132
 
133
- t3_mtl23ls_v2.safetensors: 0%| | 7.60M/2.14G [00:01<09:01, 3.94MB/s]
134
 
135
- t3_mtl23ls_v2.safetensors: 4%|β–Ž | 78.7M/2.14G [00:10<04:22, 7.88MB/s]
136
 
137
- t3_mtl23ls_v2.safetensors: 44%|β–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 935M/2.14G [00:11<00:10, 117MB/s] 
138
- t3_mtl23ls_v2.safetensors: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 2.14G/2.14G [00:12<00:00, 178MB/s]
139
- 02/07/2026 04:38:22 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/ResembleAI/chatterbox/resolve/main/s3gen.safetensors "HTTP/1.1 302 Found"
 
 
 
 
140
 
141
 
142
  s3gen.safetensors: 0%| | 0.00/1.06G [00:00<?, ?B/s]
143
 
144
- s3gen.safetensors: 6%|β–‹ | 67.1M/1.06G [00:01<00:23, 41.9MB/s]
145
 
146
- s3gen.safetensors: 37%|β–ˆβ–ˆβ–ˆβ–‹ | 386M/1.06G [00:02<00:03, 171MB/s] 
147
- s3gen.safetensors: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 1.06G/1.06G [00:03<00:00, 306MB/s]
148
- 02/07/2026 04:38:26 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/ResembleAI/chatterbox/resolve/main/mtl_tokenizer.json "HTTP/1.1 307 Temporary Redirect"
149
- 02/07/2026 04:38:26 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/api/resolve-cache/models/ResembleAI/chatterbox/05e904af2b5c7f8e482687a9d7336c5c824467d9/mtl_tokenizer.json "HTTP/1.1 200 OK"
150
- 02/07/2026 04:38:26 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/resolve-cache/models/ResembleAI/chatterbox/05e904af2b5c7f8e482687a9d7336c5c824467d9/mtl_tokenizer.json "HTTP/1.1 200 OK"
151
 
152
 
153
  mtl_tokenizer.json: 0%| | 0.00/68.1k [00:00<?, ?B/s]
154
- mtl_tokenizer.json: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 68.1k/68.1k [00:00<00:00, 66.7MB/s]
155
- 02/07/2026 04:38:26 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/ResembleAI/chatterbox/resolve/main/conds.pt "HTTP/1.1 302 Found"
156
 
157
 
158
  conds.pt: 0%| | 0.00/107k [00:00<?, ?B/s]
159
- conds.pt: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 107k/107k [00:00<00:00, 1.30MB/s]
160
- 02/07/2026 04:38:26 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/models/ResembleAI/chatterbox/revision/main "HTTP/1.1 200 OK"
161
 
162
 
163
  Downloading (incomplete total...): 0.00B [00:00, ?B/s]
164
 
165
- Fetching 6 files: 0%| | 0/6 [00:00<?, ?it/s]02/07/2026 04:38:26 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/ResembleAI/chatterbox/resolve/05e904af2b5c7f8e482687a9d7336c5c824467d9/conds.pt "HTTP/1.1 302 Found"
166
 
167
 
168
- Downloading (incomplete total...): 0%| | 0.00/107k [00:00<?, ?B/s]02/07/2026 04:38:26 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/ResembleAI/chatterbox/resolve/05e904af2b5c7f8e482687a9d7336c5c824467d9/s3gen.pt "HTTP/1.1 302 Found"
 
 
169
 
170
 
171
- Downloading (incomplete total...): 0%| | 0.00/1.06G [00:00<?, ?B/s]02/07/2026 04:38:26 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/ResembleAI/chatterbox/resolve/05e904af2b5c7f8e482687a9d7336c5c824467d9/grapheme_mtl_merged_expanded_v1.json "HTTP/1.1 307 Temporary Redirect"
172
- 02/07/2026 04:38:26 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/ResembleAI/chatterbox/resolve/05e904af2b5c7f8e482687a9d7336c5c824467d9/t3_mtl23ls_v2.safetensors "HTTP/1.1 302 Found"
173
- 02/07/2026 04:38:26 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/ResembleAI/chatterbox/resolve/05e904af2b5c7f8e482687a9d7336c5c824467d9/ve.pt "HTTP/1.1 302 Found"
174
 
175
 
176
- Downloading (incomplete total...): 0%| | 0.00/3.21G [00:00<?, ?B/s]
177
-
178
- Downloading (incomplete total...): 0%| | 0.00/3.21G [00:00<?, ?B/s]02/07/2026 04:38:26 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/ResembleAI/chatterbox/resolve/05e904af2b5c7f8e482687a9d7336c5c824467d9/Cangjie5_TC.json "HTTP/1.1 307 Temporary Redirect"
179
- 02/07/2026 04:38:26 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/api/resolve-cache/models/ResembleAI/chatterbox/05e904af2b5c7f8e482687a9d7336c5c824467d9/Cangjie5_TC.json "HTTP/1.1 200 OK"
180
- 02/07/2026 04:38:26 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/resolve-cache/models/ResembleAI/chatterbox/05e904af2b5c7f8e482687a9d7336c5c824467d9/Cangjie5_TC.json "HTTP/1.1 200 OK"
181
 
 
 
182
 
183
- Downloading (incomplete total...): 0%| | 107k/3.21G [00:00<1:02:55, 850kB/s]02/07/2026 04:38:26 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/api/resolve-cache/models/ResembleAI/chatterbox/05e904af2b5c7f8e482687a9d7336c5c824467d9/grapheme_mtl_merged_expanded_v1.json "HTTP/1.1 200 OK"
184
- 02/07/2026 04:38:26 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/resolve-cache/models/ResembleAI/chatterbox/05e904af2b5c7f8e482687a9d7336c5c824467d9/grapheme_mtl_merged_expanded_v1.json "HTTP/1.1 200 OK"
185
 
 
186
 
187
- Downloading (incomplete total...): 0%| | 7.73M/3.21G [00:00<01:31, 35.0MB/s]
188
-
189
- Downloading (incomplete total...): 0%| | 15.4M/3.21G [00:02<09:40, 5.50MB/s]
190
-
191
- Downloading (incomplete total...): 3%|β–Ž | 86.5M/3.21G [00:05<02:44, 19.0MB/s]
192
 
193
- Downloading (incomplete total...): 11%|β–ˆβ– | 367M/3.21G [00:07<00:41, 68.9MB/s] 
194
 
195
- Downloading (incomplete total...): 30%|β–ˆβ–ˆβ–ˆ | 979M/3.21G [00:08<00:12, 184MB/s] 
196
 
197
- Downloading (incomplete total...): 39%|β–ˆβ–ˆβ–ˆβ–Š | 1.24G/3.21G [00:12<00:17, 113MB/s]
198
 
199
- Downloading (incomplete total...): 62%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 2.00G/3.21G [00:13<00:05, 214MB/s]
200
 
201
- Fetching 6 files: 67%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 4/6 [00:13<00:06, 3.40s/it]
202
- Fetching 6 files: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 6/6 [00:14<00:00, 2.42s/it]
203
 
 
 
204
 
205
- Download complete: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 3.21G/3.21G [00:14<00:00, 214MB/s] 
206
 
207
- Download complete: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 3.21G/3.21G [00:24<00:00, 214MB/s]
208
- Download complete: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 3.21G/3.21G [00:24<00:00, 133MB/s]
209
  /usr/local/lib/python3.13/site-packages/diffusers/models/lora.py:393: FutureWarning: `LoRACompatibleLinear` is deprecated and will be removed in version 1.0.0. Use of `LoRACompatibleLinear` is deprecated. Please switch to PEFT backend by installing PEFT: `pip install peft`.
210
  deprecate("LoRACompatibleLinear", "1.0.0", deprecation_message)
211
- 02/07/2026 04:38:52 - INFO - root - input frame rate=25
212
- 02/07/2026 04:38:54 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/ResembleAI/chatterbox/resolve/main/Cangjie5_TC.json "HTTP/1.1 307 Temporary Redirect"
213
- 02/07/2026 04:38:54 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/api/resolve-cache/models/ResembleAI/chatterbox/05e904af2b5c7f8e482687a9d7336c5c824467d9/Cangjie5_TC.json "HTTP/1.1 200 OK"
214
- 02/07/2026 04:38:54 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/resolve-cache/models/ResembleAI/chatterbox/05e904af2b5c7f8e482687a9d7336c5c824467d9/Cangjie5_TC.json "HTTP/1.1 200 OK"
215
 
216
 
217
  Cangjie5_TC.json: 0%| | 0.00/1.92M [00:00<?, ?B/s]
218
- Cangjie5_TC.json: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 1.92M/1.92M [00:00<00:00, 26.6MB/s]
219
  Downloading: "https://github.com/explosion/spacy-pkuseg/releases/download/v0.0.26/spacy_ontonotes.zip" to /root/.pkuseg/spacy_ontonotes.zip
220
 
221
 
222
  0%| | 0/34567143 [00:00<?, ?it/s]
223
- 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 34567143/34567143 [00:00<00:00, 121241123.32it/s]
224
  Traceback (most recent call last):
225
  File "/app/chatterbox-multilingual-finetuning/src/finetune_t3.py", line 849, in <module>
226
  main()
@@ -230,9 +227,9 @@ Traceback (most recent call last):
230
  File "/app/chatterbox-multilingual-finetuning/src/chatterbox/mtl_tts.py", line 201, in from_pretrained
231
  return cls.from_local(ckpt_dir, device)
232
  ~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^
233
- File "/app/chatterbox-multilingual-finetuning/src/chatterbox/mtl_tts.py", line 179, in from_local
234
  conds = Conditionals.load(builtin_voice).to(device)
235
- File "/app/chatterbox-multilingual-finetuning/src/chatterbox/mtl_tts.py", line 96, in to
236
  self.t3 = self.t3.to(device)
237
  ~~~~~~~~~~^^^^^^^^
238
  TypeError: T3Cond.to() takes 1 positional argument but 2 were given
 
1
 
2
  /usr/local/lib/python3.13/site-packages/perth/perth_net/__init__.py:1: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81.
3
  from pkg_resources import resource_filename
4
+ 02/07/2026 05:21:50 - INFO - __main__ - Training/evaluation parameters CustomTrainingArguments(
5
  accelerator_config={'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None, 'use_configured_state': False},
6
  adam_beta1=0.9,
7
  adam_beta2=0.999,
 
113
  warmup_steps=1.0,
114
  weight_decay=0.0,
115
  )
116
+ 02/07/2026 05:21:50 - INFO - __main__ - Model parameters ModelArguments(model_name_or_path='ResembleAI/chatterbox', local_model_dir=None, cache_dir=None, freeze_voice_encoder=True, freeze_s3gen=True)
117
+ 02/07/2026 05:21:50 - INFO - __main__ - Data parameters DataArguments(language='hi', dataset_dir=None, metadata_file=None, dataset_name='rahul7star/hindi-speech-dataset', dataset_config_name=None, train_split_name='train', eval_split_name='validation', text_column_name='text_scribe', audio_column_name='audio', max_text_len=256, max_speech_len=800, audio_prompt_duration_s=3.0, eval_split_size=0.0002, preprocessing_num_workers=None, ignore_verifications=False)
118
+ 02/07/2026 05:21:50 - INFO - __main__ - Loading ChatterboxTTS model...
119
+ 02/07/2026 05:21:50 - INFO - __main__ - Loading model from Hugging Face Hub: ResembleAI/chatterbox
120
  /usr/local/lib/python3.13/site-packages/huggingface_hub/utils/_validators.py:202: UserWarning: The `local_dir_use_symlinks` argument is deprecated and ignored in `hf_hub_download`. Downloading to a local directory does not use symlinks anymore.
121
  warnings.warn(
122
+ 02/07/2026 05:21:50 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/ResembleAI/chatterbox/resolve/main/ve.safetensors "HTTP/1.1 302 Found"
123
+ 02/07/2026 05:21:50 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/models/ResembleAI/chatterbox/xet-read-token/05e904af2b5c7f8e482687a9d7336c5c824467d9 "HTTP/1.1 200 OK"
124
 
125
 
126
  ve.safetensors: 0%| | 0.00/5.70M [00:00<?, ?B/s]
127
+ ve.safetensors: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 5.70M/5.70M [00:00<00:00, 21.5MB/s]
128
+ 02/07/2026 05:21:51 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/ResembleAI/chatterbox/resolve/main/t3_mtl23ls_v2.safetensors "HTTP/1.1 302 Found"
129
 
130
 
131
  t3_mtl23ls_v2.safetensors: 0%| | 0.00/2.14G [00:00<?, ?B/s]
132
 
133
+ t3_mtl23ls_v2.safetensors: 0%| | 7.60M/2.14G [00:01<05:35, 6.37MB/s]
134
 
135
+ t3_mtl23ls_v2.safetensors: 4%|β–Ž | 78.6M/2.14G [00:04<01:49, 18.9MB/s]
136
 
137
+ t3_mtl23ls_v2.safetensors: 27%|β–ˆβ–ˆβ–‹ | 576M/2.14G [00:06<00:15, 102MB/s] 
138
+
139
+ t3_mtl23ls_v2.safetensors: 34%|β–ˆβ–ˆβ–ˆβ–Ž | 719M/2.14G [00:08<00:14, 97.7MB/s]
140
+
141
+ t3_mtl23ls_v2.safetensors: 67%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 1.43G/2.14G [00:09<00:03, 224MB/s]
142
+ t3_mtl23ls_v2.safetensors: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 2.14G/2.14G [00:10<00:00, 207MB/s]
143
+ 02/07/2026 05:22:01 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/ResembleAI/chatterbox/resolve/main/s3gen.safetensors "HTTP/1.1 302 Found"
144
 
145
 
146
  s3gen.safetensors: 0%| | 0.00/1.06G [00:00<?, ?B/s]
147
 
148
+ s3gen.safetensors: 5%|▍ | 50.7M/1.06G [00:01<00:34, 29.2MB/s]
149
 
150
+ s3gen.safetensors: 30%|β–ˆβ–ˆβ–ˆ | 319M/1.06G [00:02<00:05, 137MB/s] 
151
+ s3gen.safetensors: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 1.06G/1.06G [00:03<00:00, 335MB/s]
152
+ 02/07/2026 05:22:04 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/ResembleAI/chatterbox/resolve/main/mtl_tokenizer.json "HTTP/1.1 307 Temporary Redirect"
153
+ 02/07/2026 05:22:04 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/api/resolve-cache/models/ResembleAI/chatterbox/05e904af2b5c7f8e482687a9d7336c5c824467d9/mtl_tokenizer.json "HTTP/1.1 200 OK"
154
+ 02/07/2026 05:22:04 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/resolve-cache/models/ResembleAI/chatterbox/05e904af2b5c7f8e482687a9d7336c5c824467d9/mtl_tokenizer.json "HTTP/1.1 200 OK"
155
 
156
 
157
  mtl_tokenizer.json: 0%| | 0.00/68.1k [00:00<?, ?B/s]
158
+ mtl_tokenizer.json: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 68.1k/68.1k [00:00<00:00, 86.5MB/s]
159
+ 02/07/2026 05:22:04 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/ResembleAI/chatterbox/resolve/main/conds.pt "HTTP/1.1 302 Found"
160
 
161
 
162
  conds.pt: 0%| | 0.00/107k [00:00<?, ?B/s]
163
+ conds.pt: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 107k/107k [00:00<00:00, 1.14MB/s]
164
+ 02/07/2026 05:22:04 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/models/ResembleAI/chatterbox/revision/main "HTTP/1.1 200 OK"
165
 
166
 
167
  Downloading (incomplete total...): 0.00B [00:00, ?B/s]
168
 
169
+ Fetching 5 files: 0%| | 0/5 [00:00<?, ?it/s]02/07/2026 05:22:04 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/ResembleAI/chatterbox/resolve/05e904af2b5c7f8e482687a9d7336c5c824467d9/conds.pt "HTTP/1.1 302 Found"
170
 
171
 
172
+ Downloading (incomplete total...): 0%| | 0.00/107k [00:00<?, ?B/s]02/07/2026 05:22:04 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/ResembleAI/chatterbox/resolve/05e904af2b5c7f8e482687a9d7336c5c824467d9/grapheme_mtl_merged_expanded_v1.json "HTTP/1.1 307 Temporary Redirect"
173
+ 02/07/2026 05:22:04 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/ResembleAI/chatterbox/resolve/05e904af2b5c7f8e482687a9d7336c5c824467d9/s3gen.pt "HTTP/1.1 302 Found"
174
+ 02/07/2026 05:22:04 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/ResembleAI/chatterbox/resolve/05e904af2b5c7f8e482687a9d7336c5c824467d9/t3_mtl23ls_v2.safetensors "HTTP/1.1 302 Found"
175
 
176
 
177
+ Downloading (incomplete total...): 0%| | 0.00/2.14G [00:00<?, ?B/s]02/07/2026 05:22:04 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/ResembleAI/chatterbox/resolve/05e904af2b5c7f8e482687a9d7336c5c824467d9/ve.pt "HTTP/1.1 302 Found"
 
 
178
 
179
 
180
+ Downloading (incomplete total...): 0%| | 0.00/3.20G [00:00<?, ?B/s]
 
 
 
 
181
 
182
+ Downloading (incomplete total...): 0%| | 0.00/3.21G [00:00<?, ?B/s]02/07/2026 05:22:04 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/api/resolve-cache/models/ResembleAI/chatterbox/05e904af2b5c7f8e482687a9d7336c5c824467d9/grapheme_mtl_merged_expanded_v1.json "HTTP/1.1 200 OK"
183
+ 02/07/2026 05:22:04 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/resolve-cache/models/ResembleAI/chatterbox/05e904af2b5c7f8e482687a9d7336c5c824467d9/grapheme_mtl_merged_expanded_v1.json "HTTP/1.1 200 OK"
184
 
 
 
185
 
186
+ Downloading (incomplete total...): 0%| | 0.00/3.21G [00:00<?, ?B/s]
187
 
188
+ Downloading (incomplete total...): 0%| | 13.5M/3.21G [00:02<10:16, 5.18MB/s]
 
 
 
 
189
 
190
+ Downloading (incomplete total...): 4%|▍ | 136M/3.21G [00:04<01:31, 33.7MB/s] 
191
 
192
+ Downloading (incomplete total...): 13%|β–ˆβ–Ž | 412M/3.21G [00:05<00:28, 97.6MB/s]
193
 
194
+ Downloading (incomplete total...): 28%|β–ˆβ–ˆβ–Š | 894M/3.21G [00:08<00:17, 135MB/s] 
195
 
196
+ Downloading (incomplete total...): 34%|β–ˆβ–ˆβ–ˆβ– | 1.10G/3.21G [00:11<00:20, 103MB/s]
197
 
198
+ Downloading (incomplete total...): 67%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 2.14G/3.21G [00:12<00:04, 259MB/s]
 
199
 
200
+ Fetching 5 files: 60%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 3/5 [00:13<00:08, 4.46s/it]
201
+ Fetching 5 files: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 5/5 [00:13<00:00, 2.68s/it]
202
 
 
203
 
204
+ Download complete: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 3.21G/3.21G [00:13<00:00, 259MB/s] 
205
+ Download complete: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 3.21G/3.21G [00:22<00:00, 140MB/s]
206
  /usr/local/lib/python3.13/site-packages/diffusers/models/lora.py:393: FutureWarning: `LoRACompatibleLinear` is deprecated and will be removed in version 1.0.0. Use of `LoRACompatibleLinear` is deprecated. Please switch to PEFT backend by installing PEFT: `pip install peft`.
207
  deprecate("LoRACompatibleLinear", "1.0.0", deprecation_message)
208
+ 02/07/2026 05:22:29 - INFO - root - input frame rate=25
209
+ 02/07/2026 05:22:34 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/ResembleAI/chatterbox/resolve/main/Cangjie5_TC.json "HTTP/1.1 307 Temporary Redirect"
210
+ 02/07/2026 05:22:34 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/api/resolve-cache/models/ResembleAI/chatterbox/05e904af2b5c7f8e482687a9d7336c5c824467d9/Cangjie5_TC.json "HTTP/1.1 200 OK"
211
+ 02/07/2026 05:22:34 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/resolve-cache/models/ResembleAI/chatterbox/05e904af2b5c7f8e482687a9d7336c5c824467d9/Cangjie5_TC.json "HTTP/1.1 200 OK"
212
 
213
 
214
  Cangjie5_TC.json: 0%| | 0.00/1.92M [00:00<?, ?B/s]
215
+ Cangjie5_TC.json: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 1.92M/1.92M [00:00<00:00, 23.0MB/s]
216
  Downloading: "https://github.com/explosion/spacy-pkuseg/releases/download/v0.0.26/spacy_ontonotes.zip" to /root/.pkuseg/spacy_ontonotes.zip
217
 
218
 
219
  0%| | 0/34567143 [00:00<?, ?it/s]
220
+ 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 34567143/34567143 [00:00<00:00, 159733455.87it/s]
221
  Traceback (most recent call last):
222
  File "/app/chatterbox-multilingual-finetuning/src/finetune_t3.py", line 849, in <module>
223
  main()
 
227
  File "/app/chatterbox-multilingual-finetuning/src/chatterbox/mtl_tts.py", line 201, in from_pretrained
228
  return cls.from_local(ckpt_dir, device)
229
  ~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^
230
+ File "/app/chatterbox-multilingual-finetuning/src/chatterbox/mtl_tts.py", line 180, in from_local
231
  conds = Conditionals.load(builtin_voice).to(device)
232
+ File "/app/chatterbox-multilingual-finetuning/src/chatterbox/mtl_tts.py", line 106, in to
233
  self.t3 = self.t3.to(device)
234
  ~~~~~~~~~~^^^^^^^^
235
  TypeError: T3Cond.to() takes 1 positional argument but 2 were given