Chatterbox fine-tuned model + logs
Browse files
runs/Feb07_05-59-59_r-rahul7star-chatterbox-train-632mlseq-2bdf1-zs65l/events.out.tfevents.1770440399.r-rahul7star-chatterbox-train-632mlseq-2bdf1-zs65l.132.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:77940f14a9d8fe36e16dea79e74e33cf438976b5864ac506a3c6e6a5037eb7cc
|
| 3 |
+
size 4097
|
training.log
CHANGED
|
@@ -8,7 +8,7 @@ loaded PerthNet (Implicit) at step 250,000
|
|
| 8 |
|
| 9 |
/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.
|
| 10 |
from pkg_resources import resource_filename
|
| 11 |
-
02/07/2026 05:
|
| 12 |
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},
|
| 13 |
adam_beta1=0.9,
|
| 14 |
adam_beta2=0.999,
|
|
@@ -120,116 +120,574 @@ warmup_ratio=None,
|
|
| 120 |
warmup_steps=1.0,
|
| 121 |
weight_decay=0.0,
|
| 122 |
)
|
| 123 |
-
02/07/2026 05:
|
| 124 |
-
02/07/2026 05:
|
| 125 |
-
02/07/2026 05:
|
| 126 |
-
02/07/2026 05:
|
| 127 |
-
02/07/2026 05:
|
| 128 |
-
02/07/2026 05:
|
| 129 |
-
02/07/2026 05:
|
| 130 |
-
02/07/2026 05:
|
| 131 |
-
02/07/2026 05:
|
| 132 |
-
02/07/2026 05:
|
| 133 |
|
| 134 |
|
| 135 |
Downloading (incomplete total...): 0.00B [00:00, ?B/s][A
|
| 136 |
|
| 137 |
-
Fetching 5 files: 0%| | 0/5 [00:00<?, ?it/s][A02/07/2026 05:
|
| 138 |
-
02/07/2026 05:
|
| 139 |
-
02/07/2026 05:
|
| 140 |
-
02/07/2026 05:
|
| 141 |
-
02/07/2026 05:
|
| 142 |
-
02/07/2026 05:
|
| 143 |
-
02/07/2026 05:
|
| 144 |
|
| 145 |
|
| 146 |
-
Downloading (incomplete total...): 0%| | 0.00/
|
| 147 |
|
| 148 |
|
| 149 |
-
Downloading (incomplete total...): 0%| | 0.00/
|
| 150 |
|
|
|
|
| 151 |
|
| 152 |
-
Downloading (incomplete total...): 0%| | 0.00/3.
|
| 153 |
|
|
|
|
| 154 |
|
| 155 |
-
Downloading (incomplete total...): 0%| | 0.00/3.20G [00:00<?, ?B/s][A02/07/2026 05:45:31 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/models/ResembleAI/chatterbox/xet-read-token/05e904af2b5c7f8e482687a9d7336c5c824467d9 "HTTP/1.1 200 OK"
|
| 156 |
|
|
|
|
| 157 |
|
| 158 |
-
Downloading (incomplete total...): 0%| |
|
| 159 |
|
| 160 |
-
Downloading (incomplete total...):
|
| 161 |
|
| 162 |
-
Downloading (incomplete total...):
|
| 163 |
|
| 164 |
-
Downloading (incomplete total...):
|
| 165 |
|
| 166 |
-
Downloading (incomplete total...):
|
| 167 |
|
| 168 |
-
|
|
|
|
| 169 |
|
| 170 |
-
Downloading (incomplete total...): 45%|βββββ | 1.45G/3.21G [00:11<00:09, 179MB/s][A
|
| 171 |
|
| 172 |
-
|
| 173 |
-
|
| 174 |
-
Fetching 5 files: 60%|ββββββ | 3/5 [00:13<00:08, 4.38s/it][A
|
| 175 |
-
Fetching 5 files: 100%|ββββββββββ| 5/5 [00:13<00:00, 2.73s/it]
|
| 176 |
-
|
| 177 |
-
|
| 178 |
-
Download complete: 100%|ββββββββββ| 3.21G/3.21G [00:13<00:00, 300MB/s] [A
|
| 179 |
-
Download complete: 100%|ββββββββββ| 3.21G/3.21G [00:20<00:00, 156MB/s]
|
| 180 |
/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`.
|
| 181 |
deprecate("LoRACompatibleLinear", "1.0.0", deprecation_message)
|
| 182 |
-
02/07/2026 05:
|
| 183 |
-
02/07/2026 05:
|
| 184 |
-
02/07/2026 05:
|
| 185 |
-
02/07/2026 05:
|
| 186 |
|
| 187 |
|
| 188 |
Cangjie5_TC.json: 0%| | 0.00/1.92M [00:00<?, ?B/s][A
|
| 189 |
-
Cangjie5_TC.json: 100%|ββββββββββ| 1.92M/1.92M [00:00<00:00,
|
| 190 |
Downloading: "https://github.com/explosion/spacy-pkuseg/releases/download/v0.0.26/spacy_ontonotes.zip" to /root/.pkuseg/spacy_ontonotes.zip
|
| 191 |
|
| 192 |
|
| 193 |
0%| | 0/34567143 [00:00<?, ?it/s][A
|
| 194 |
-
100%|ββββββββββ| 34567143/34567143 [00:00<00:00,
|
| 195 |
-
02/07/2026 05:
|
| 196 |
-
02/07/2026 05:
|
| 197 |
-
02/07/2026 05:
|
| 198 |
-
02/07/2026 05:
|
| 199 |
-
02/07/2026 05:
|
| 200 |
-
02/07/2026 05:
|
| 201 |
-
02/07/2026 05:
|
| 202 |
-
02/07/2026 05:
|
| 203 |
-
|
| 204 |
-
|
| 205 |
-
README.md: 0%| | 0.00/
|
| 206 |
-
README.md: 100%|ββββββββββ|
|
| 207 |
-
02/07/2026 05:
|
| 208 |
-
02/07/2026 05:
|
| 209 |
-
02/07/2026 05:
|
| 210 |
-
02/07/2026 05:
|
| 211 |
-
02/07/2026 05:
|
| 212 |
-
02/07/2026 05:
|
| 213 |
-
02/07/2026 05:
|
| 214 |
-
02/07/2026 05:
|
| 215 |
-
|
| 216 |
-
02/07/2026 05:
|
| 217 |
-
|
| 218 |
-
|
| 219 |
-
|
| 220 |
-
data/train-00000-of-
|
| 221 |
-
|
| 222 |
-
|
| 223 |
-
|
| 224 |
-
|
| 225 |
-
|
| 226 |
-
|
| 227 |
-
|
| 228 |
-
|
| 229 |
-
|
| 230 |
-
|
| 231 |
-
|
| 232 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 233 |
File "/app/chatterbox-multilingual-finetuning/src/finetune_t3.py", line 849, in <module>
|
| 234 |
main()
|
| 235 |
~~~~^^
|
|
@@ -254,15 +712,35 @@ Traceback (most recent call last):
|
|
| 254 |
...<5 lines>...
|
| 255 |
metric_key_prefix=metric_key_prefix,
|
| 256 |
)
|
| 257 |
-
File "/usr/local/lib/python3.13/site-packages/transformers/trainer.py", line
|
| 258 |
-
|
| 259 |
-
|
| 260 |
-
File "/usr/local/lib/python3.13/site-packages/
|
| 261 |
-
|
| 262 |
-
File "/usr/local/lib/python3.13/site-packages/
|
| 263 |
-
|
| 264 |
-
|
| 265 |
-
)
|
| 266 |
-
|
| 267 |
-
|
| 268 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
|
| 9 |
/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.
|
| 10 |
from pkg_resources import resource_filename
|
| 11 |
+
02/07/2026 05:57:04 - INFO - __main__ - Training/evaluation parameters CustomTrainingArguments(
|
| 12 |
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},
|
| 13 |
adam_beta1=0.9,
|
| 14 |
adam_beta2=0.999,
|
|
|
|
| 120 |
warmup_steps=1.0,
|
| 121 |
weight_decay=0.0,
|
| 122 |
)
|
| 123 |
+
02/07/2026 05:57:04 - INFO - __main__ - Model parameters ModelArguments(model_name_or_path='/app/hf_cache/models--ResembleAI--chatterbox/snapshots/05e904af2b5c7f8e482687a9d7336c5c824467d9', local_model_dir=None, cache_dir=None, freeze_voice_encoder=True, freeze_s3gen=True)
|
| 124 |
+
02/07/2026 05:57:04 - 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)
|
| 125 |
+
02/07/2026 05:57:04 - INFO - __main__ - Loading ChatterboxTTS model...
|
| 126 |
+
02/07/2026 05:57:04 - INFO - __main__ - Loading model from Hugging Face Hub: /app/hf_cache/models--ResembleAI--chatterbox/snapshots/05e904af2b5c7f8e482687a9d7336c5c824467d9
|
| 127 |
+
02/07/2026 05:57:04 - WARNING - __main__ - Could not download ve.safetensors from /app/hf_cache/models--ResembleAI--chatterbox/snapshots/05e904af2b5c7f8e482687a9d7336c5c824467d9: Repo id must be in the form 'repo_name' or 'namespace/repo_name': '/app/hf_cache/models--ResembleAI--chatterbox/snapshots/05e904af2b5c7f8e482687a9d7336c5c824467d9'. Use `repo_type` argument if needed..
|
| 128 |
+
02/07/2026 05:57:04 - WARNING - __main__ - Could not download t3_mtl23ls_v2.safetensors from /app/hf_cache/models--ResembleAI--chatterbox/snapshots/05e904af2b5c7f8e482687a9d7336c5c824467d9: Repo id must be in the form 'repo_name' or 'namespace/repo_name': '/app/hf_cache/models--ResembleAI--chatterbox/snapshots/05e904af2b5c7f8e482687a9d7336c5c824467d9'. Use `repo_type` argument if needed..
|
| 129 |
+
02/07/2026 05:57:04 - WARNING - __main__ - Could not download s3gen.safetensors from /app/hf_cache/models--ResembleAI--chatterbox/snapshots/05e904af2b5c7f8e482687a9d7336c5c824467d9: Repo id must be in the form 'repo_name' or 'namespace/repo_name': '/app/hf_cache/models--ResembleAI--chatterbox/snapshots/05e904af2b5c7f8e482687a9d7336c5c824467d9'. Use `repo_type` argument if needed..
|
| 130 |
+
02/07/2026 05:57:04 - WARNING - __main__ - Could not download mtl_tokenizer.json from /app/hf_cache/models--ResembleAI--chatterbox/snapshots/05e904af2b5c7f8e482687a9d7336c5c824467d9: Repo id must be in the form 'repo_name' or 'namespace/repo_name': '/app/hf_cache/models--ResembleAI--chatterbox/snapshots/05e904af2b5c7f8e482687a9d7336c5c824467d9'. Use `repo_type` argument if needed..
|
| 131 |
+
02/07/2026 05:57:04 - INFO - __main__ - conds.pt not found on Hub or failed to download for this model.
|
| 132 |
+
02/07/2026 05:57:04 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/models/ResembleAI/chatterbox/revision/main "HTTP/1.1 200 OK"
|
| 133 |
|
| 134 |
|
| 135 |
Downloading (incomplete total...): 0.00B [00:00, ?B/s][A
|
| 136 |
|
| 137 |
+
Fetching 5 files: 0%| | 0/5 [00:00<?, ?it/s][A02/07/2026 05:57:04 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/ResembleAI/chatterbox/resolve/05e904af2b5c7f8e482687a9d7336c5c824467d9/s3gen.pt "HTTP/1.1 302 Found"
|
| 138 |
+
02/07/2026 05:57:04 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/ResembleAI/chatterbox/resolve/05e904af2b5c7f8e482687a9d7336c5c824467d9/grapheme_mtl_merged_expanded_v1.json "HTTP/1.1 307 Temporary Redirect"
|
| 139 |
+
02/07/2026 05:57:04 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/ResembleAI/chatterbox/resolve/05e904af2b5c7f8e482687a9d7336c5c824467d9/t3_mtl23ls_v2.safetensors "HTTP/1.1 302 Found"
|
| 140 |
+
02/07/2026 05:57:04 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/ResembleAI/chatterbox/resolve/05e904af2b5c7f8e482687a9d7336c5c824467d9/conds.pt "HTTP/1.1 302 Found"
|
| 141 |
+
02/07/2026 05:57:04 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/ResembleAI/chatterbox/resolve/05e904af2b5c7f8e482687a9d7336c5c824467d9/ve.pt "HTTP/1.1 302 Found"
|
| 142 |
+
02/07/2026 05:57:04 - 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"
|
| 143 |
+
02/07/2026 05:57:04 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/models/ResembleAI/chatterbox/xet-read-token/05e904af2b5c7f8e482687a9d7336c5c824467d9 "HTTP/1.1 200 OK"
|
| 144 |
|
| 145 |
|
| 146 |
+
Downloading (incomplete total...): 0%| | 0.00/1.06G [00:00<?, ?B/s][A02/07/2026 05:57:05 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/models/ResembleAI/chatterbox/xet-read-token/05e904af2b5c7f8e482687a9d7336c5c824467d9 "HTTP/1.1 200 OK"
|
| 147 |
|
| 148 |
|
| 149 |
+
Downloading (incomplete total...): 0%| | 0.00/3.20G [00:00<?, ?B/s][A02/07/2026 05:57:05 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/models/ResembleAI/chatterbox/xet-read-token/05e904af2b5c7f8e482687a9d7336c5c824467d9 "HTTP/1.1 200 OK"
|
| 150 |
|
| 151 |
+
02/07/2026 05:57:05 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/models/ResembleAI/chatterbox/xet-read-token/05e904af2b5c7f8e482687a9d7336c5c824467d9 "HTTP/1.1 200 OK"
|
| 152 |
|
| 153 |
+
Downloading (incomplete total...): 0%| | 0.00/3.21G [00:00<?, ?B/s][A
|
| 154 |
|
| 155 |
+
Downloading (incomplete total...): 0%| | 0.00/3.21G [00:00<?, ?B/s][A02/07/2026 05:57:05 - 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"
|
| 156 |
|
|
|
|
| 157 |
|
| 158 |
+
Downloading (incomplete total...): 0%| | 0.00/3.21G [00:00<?, ?B/s][A
|
| 159 |
|
| 160 |
+
Downloading (incomplete total...): 0%| | 13.5M/3.21G [00:02<09:19, 5.71MB/s][A
|
| 161 |
|
| 162 |
+
Downloading (incomplete total...): 3%|β | 80.5M/3.21G [00:06<04:04, 12.8MB/s][A
|
| 163 |
|
| 164 |
+
Downloading (incomplete total...): 4%|β | 132M/3.21G [00:08<03:03, 16.7MB/s] [A
|
| 165 |
|
| 166 |
+
Downloading (incomplete total...): 21%|ββ | 672M/3.21G [00:09<00:22, 113MB/s] [A
|
| 167 |
|
| 168 |
+
Downloading (incomplete total...): 56%|ββββββ | 1.79G/3.21G [00:10<00:04, 320MB/s][A
|
| 169 |
|
| 170 |
+
Fetching 5 files: 60%|ββββββ | 3/5 [00:10<00:07, 3.66s/it][A
|
| 171 |
+
Fetching 5 files: 100%|ββββββββββ| 5/5 [00:11<00:00, 2.37s/it]
|
| 172 |
|
|
|
|
| 173 |
|
| 174 |
+
Download complete: 100%|ββββββββββ| 3.21G/3.21G [00:11<00:00, 320MB/s] [A
|
| 175 |
+
Download complete: 100%|ββββββββββ| 3.21G/3.21G [00:18<00:00, 173MB/s]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 176 |
/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`.
|
| 177 |
deprecate("LoRACompatibleLinear", "1.0.0", deprecation_message)
|
| 178 |
+
02/07/2026 05:57:24 - INFO - root - input frame rate=25
|
| 179 |
+
02/07/2026 05:57:26 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/ResembleAI/chatterbox/resolve/main/Cangjie5_TC.json "HTTP/1.1 307 Temporary Redirect"
|
| 180 |
+
02/07/2026 05:57:26 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/api/resolve-cache/models/ResembleAI/chatterbox/05e904af2b5c7f8e482687a9d7336c5c824467d9/Cangjie5_TC.json "HTTP/1.1 200 OK"
|
| 181 |
+
02/07/2026 05:57:26 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/resolve-cache/models/ResembleAI/chatterbox/05e904af2b5c7f8e482687a9d7336c5c824467d9/Cangjie5_TC.json "HTTP/1.1 200 OK"
|
| 182 |
|
| 183 |
|
| 184 |
Cangjie5_TC.json: 0%| | 0.00/1.92M [00:00<?, ?B/s][A
|
| 185 |
+
Cangjie5_TC.json: 100%|ββββββββββ| 1.92M/1.92M [00:00<00:00, 38.8MB/s]
|
| 186 |
Downloading: "https://github.com/explosion/spacy-pkuseg/releases/download/v0.0.26/spacy_ontonotes.zip" to /root/.pkuseg/spacy_ontonotes.zip
|
| 187 |
|
| 188 |
|
| 189 |
0%| | 0/34567143 [00:00<?, ?it/s][A
|
| 190 |
+
100%|ββββββββββ| 34567143/34567143 [00:00<00:00, 227533621.39it/s]
|
| 191 |
+
02/07/2026 05:57:28 - INFO - __main__ - Voice Encoder frozen.
|
| 192 |
+
02/07/2026 05:57:28 - INFO - __main__ - S3Gen model frozen.
|
| 193 |
+
02/07/2026 05:57:28 - INFO - __main__ - T3 model set to trainable.
|
| 194 |
+
02/07/2026 05:57:28 - INFO - __main__ - Loading and processing dataset...
|
| 195 |
+
02/07/2026 05:57:28 - INFO - __main__ - Loading dataset 'rahul7star/hindi-speech-dataset' from Hugging Face Hub.
|
| 196 |
+
02/07/2026 05:57:28 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/datasets/rahul7star/hindi-speech-dataset/resolve/main/README.md "HTTP/1.1 307 Temporary Redirect"
|
| 197 |
+
02/07/2026 05:57:28 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/api/resolve-cache/datasets/rahul7star/hindi-speech-dataset/0bfd5e2e4555ec80d7dd74b10442836d2e169be6/README.md "HTTP/1.1 200 OK"
|
| 198 |
+
02/07/2026 05:57:28 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/resolve-cache/datasets/rahul7star/hindi-speech-dataset/0bfd5e2e4555ec80d7dd74b10442836d2e169be6/README.md "HTTP/1.1 200 OK"
|
| 199 |
+
|
| 200 |
+
|
| 201 |
+
README.md: 0%| | 0.00/591 [00:00<?, ?B/s][A
|
| 202 |
+
README.md: 100%|ββββββββββ| 591/591 [00:00<00:00, 3.47MB/s]
|
| 203 |
+
02/07/2026 05:57:28 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/datasets/rahul7star/hindi-speech-dataset/resolve/0bfd5e2e4555ec80d7dd74b10442836d2e169be6/hindi-speech-dataset.py "HTTP/1.1 404 Not Found"
|
| 204 |
+
02/07/2026 05:57:28 - INFO - httpx - HTTP Request: HEAD https://s3.amazonaws.com/datasets.huggingface.co/datasets/datasets/rahul7star/hindi-speech-dataset/rahul7star/hindi-speech-dataset.py "HTTP/1.1 404 Not Found"
|
| 205 |
+
02/07/2026 05:57:28 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/datasets/rahul7star/hindi-speech-dataset/revision/0bfd5e2e4555ec80d7dd74b10442836d2e169be6 "HTTP/1.1 200 OK"
|
| 206 |
+
02/07/2026 05:57:28 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/datasets/rahul7star/hindi-speech-dataset/resolve/0bfd5e2e4555ec80d7dd74b10442836d2e169be6/.huggingface.yaml "HTTP/1.1 404 Not Found"
|
| 207 |
+
02/07/2026 05:57:28 - INFO - httpx - HTTP Request: GET https://datasets-server.huggingface.co/info?dataset=rahul7star/hindi-speech-dataset "HTTP/1.1 200 OK"
|
| 208 |
+
02/07/2026 05:57:28 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/datasets/rahul7star/hindi-speech-dataset/tree/0bfd5e2e4555ec80d7dd74b10442836d2e169be6/data?recursive=true&expand=false "HTTP/1.1 200 OK"
|
| 209 |
+
02/07/2026 05:57:28 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/datasets/rahul7star/hindi-speech-dataset/tree/0bfd5e2e4555ec80d7dd74b10442836d2e169be6?recursive=false&expand=false "HTTP/1.1 200 OK"
|
| 210 |
+
02/07/2026 05:57:28 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/datasets/rahul7star/hindi-speech-dataset/resolve/0bfd5e2e4555ec80d7dd74b10442836d2e169be6/dataset_infos.json "HTTP/1.1 404 Not Found"
|
| 211 |
+
|
| 212 |
+
Downloading data: 0%| | 0/36 [00:00<?, ?files/s]02/07/2026 05:57:28 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/datasets/rahul7star/hindi-speech-dataset/resolve/0bfd5e2e4555ec80d7dd74b10442836d2e169be6/data/train-00000-of-00036.parquet "HTTP/1.1 302 Found"
|
| 213 |
+
02/07/2026 05:57:28 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/datasets/rahul7star/hindi-speech-dataset/xet-read-token/0bfd5e2e4555ec80d7dd74b10442836d2e169be6 "HTTP/1.1 200 OK"
|
| 214 |
+
|
| 215 |
+
|
| 216 |
+
data/train-00000-of-00036.parquet: 0%| | 0.00/1.77G [00:00<?, ?B/s][A
|
| 217 |
+
|
| 218 |
+
data/train-00000-of-00036.parquet: 0%| | 3.48M/1.77G [00:01<08:26, 3.48MB/s][A
|
| 219 |
+
|
| 220 |
+
data/train-00000-of-00036.parquet: 12%|ββ | 208M/1.77G [00:02<00:12, 122MB/s] [A
|
| 221 |
+
|
| 222 |
+
data/train-00000-of-00036.parquet: 33%|ββββ | 585M/1.77G [00:03<00:04, 237MB/s][A
|
| 223 |
+
|
| 224 |
+
data/train-00000-of-00036.parquet: 52%|ββββββ | 922M/1.77G [00:04<00:03, 276MB/s][A
|
| 225 |
+
|
| 226 |
+
data/train-00000-of-00036.parquet: 85%|βββββββββ | 1.50G/1.77G [00:05<00:00, 372MB/s][A
|
| 227 |
+
data/train-00000-of-00036.parquet: 100%|ββββββββββ| 1.77G/1.77G [00:05<00:00, 316MB/s]
|
| 228 |
+
|
| 229 |
+
Downloading data: 3%|β | 1/36 [00:05<03:17, 5.64s/files]02/07/2026 05:57:34 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/datasets/rahul7star/hindi-speech-dataset/resolve/0bfd5e2e4555ec80d7dd74b10442836d2e169be6/data/train-00001-of-00036.parquet "HTTP/1.1 302 Found"
|
| 230 |
+
|
| 231 |
+
|
| 232 |
+
data/train-00001-of-00036.parquet: 0%| | 0.00/496M [00:00<?, ?B/s][A
|
| 233 |
+
|
| 234 |
+
data/train-00001-of-00036.parquet: 5%|β | 26.1M/496M [00:01<00:18, 26.0MB/s][A
|
| 235 |
+
data/train-00001-of-00036.parquet: 100%|ββββββββββ| 496M/496M [00:01<00:00, 253MB/s]
|
| 236 |
+
|
| 237 |
+
Downloading data: 6%|β | 2/36 [00:07<02:00, 3.53s/files]02/07/2026 05:57:36 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/datasets/rahul7star/hindi-speech-dataset/resolve/0bfd5e2e4555ec80d7dd74b10442836d2e169be6/data/train-00002-of-00036.parquet "HTTP/1.1 302 Found"
|
| 238 |
+
|
| 239 |
+
|
| 240 |
+
data/train-00002-of-00036.parquet: 0%| | 0.00/461M [00:00<?, ?B/s][A
|
| 241 |
+
|
| 242 |
+
data/train-00002-of-00036.parquet: 9%|β | 41.2M/461M [00:01<00:10, 41.2MB/s][A
|
| 243 |
+
|
| 244 |
+
data/train-00002-of-00036.parquet: 100%|ββββββββββ| 461M/461M [00:02<00:00, 257MB/s] [A
|
| 245 |
+
data/train-00002-of-00036.parquet: 100%|ββββββββββ| 461M/461M [00:02<00:00, 225MB/s]
|
| 246 |
+
|
| 247 |
+
Downloading data: 8%|β | 3/36 [00:09<01:34, 2.88s/files]02/07/2026 05:57:38 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/datasets/rahul7star/hindi-speech-dataset/resolve/0bfd5e2e4555ec80d7dd74b10442836d2e169be6/data/train-00003-of-00036.parquet "HTTP/1.1 302 Found"
|
| 248 |
+
|
| 249 |
+
|
| 250 |
+
data/train-00003-of-00036.parquet: 0%| | 0.00/372M [00:00<?, ?B/s][A
|
| 251 |
+
|
| 252 |
+
data/train-00003-of-00036.parquet: 15%|ββ | 57.6M/372M [00:01<00:05, 57.4MB/s][A
|
| 253 |
+
data/train-00003-of-00036.parquet: 100%|βββββοΏ½οΏ½οΏ½ββββ| 372M/372M [00:01<00:00, 227MB/s]
|
| 254 |
+
|
| 255 |
+
Downloading data: 11%|β | 4/36 [00:11<01:16, 2.40s/files]02/07/2026 05:57:40 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/datasets/rahul7star/hindi-speech-dataset/resolve/0bfd5e2e4555ec80d7dd74b10442836d2e169be6/data/train-00004-of-00036.parquet "HTTP/1.1 302 Found"
|
| 256 |
+
|
| 257 |
+
|
| 258 |
+
data/train-00004-of-00036.parquet: 0%| | 0.00/373M [00:00<?, ?B/s][A
|
| 259 |
+
|
| 260 |
+
data/train-00004-of-00036.parquet: 13%|ββ | 50.3M/373M [00:01<00:06, 50.3MB/s][A
|
| 261 |
+
data/train-00004-of-00036.parquet: 100%|ββββββββββ| 373M/373M [00:01<00:00, 242MB/s]
|
| 262 |
+
|
| 263 |
+
Downloading data: 14%|ββ | 5/36 [00:13<01:05, 2.10s/files]02/07/2026 05:57:41 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/datasets/rahul7star/hindi-speech-dataset/resolve/0bfd5e2e4555ec80d7dd74b10442836d2e169be6/data/train-00005-of-00036.parquet "HTTP/1.1 302 Found"
|
| 264 |
+
|
| 265 |
+
|
| 266 |
+
data/train-00005-of-00036.parquet: 0%| | 0.00/841M [00:00<?, ?B/s][A
|
| 267 |
+
|
| 268 |
+
data/train-00005-of-00036.parquet: 5%|β | 44.0M/841M [00:01<00:18, 44.0MB/s][A
|
| 269 |
+
|
| 270 |
+
data/train-00005-of-00036.parquet: 34%|ββββ | 285M/841M [00:02<00:03, 159MB/s] [A
|
| 271 |
+
|
| 272 |
+
data/train-00005-of-00036.parquet: 100%|ββββββββββ| 841M/841M [00:03<00:00, 275MB/s][A
|
| 273 |
+
data/train-00005-of-00036.parquet: 100%|ββββββββββ| 841M/841M [00:03<00:00, 239MB/s]
|
| 274 |
+
|
| 275 |
+
Downloading data: 17%|ββ | 6/36 [00:16<01:17, 2.59s/files]02/07/2026 05:57:45 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/datasets/rahul7star/hindi-speech-dataset/resolve/0bfd5e2e4555ec80d7dd74b10442836d2e169be6/data/train-00006-of-00036.parquet "HTTP/1.1 302 Found"
|
| 276 |
+
|
| 277 |
+
|
| 278 |
+
data/train-00006-of-00036.parquet: 0%| | 0.00/837M [00:00<?, ?B/s][A
|
| 279 |
+
|
| 280 |
+
data/train-00006-of-00036.parquet: 4%|β | 37.4M/837M [00:01<00:21, 37.1MB/s][A
|
| 281 |
+
|
| 282 |
+
data/train-00006-of-00036.parquet: 40%|ββββ | 336M/837M [00:02<00:02, 190MB/s] [A
|
| 283 |
+
|
| 284 |
+
data/train-00006-of-00036.parquet: 100%|ββββββββββ| 837M/837M [00:03<00:00, 305MB/s][A
|
| 285 |
+
data/train-00006-of-00036.parquet: 100%|ββββββββββ| 837M/837M [00:03<00:00, 261MB/s]
|
| 286 |
+
|
| 287 |
+
Downloading data: 19%|ββ | 7/36 [00:19<01:21, 2.80s/files]02/07/2026 05:57:48 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/datasets/rahul7star/hindi-speech-dataset/resolve/0bfd5e2e4555ec80d7dd74b10442836d2e169be6/data/train-00007-of-00036.parquet "HTTP/1.1 302 Found"
|
| 288 |
+
|
| 289 |
+
|
| 290 |
+
data/train-00007-of-00036.parquet: 0%| | 0.00/618M [00:00<?, ?B/s][A
|
| 291 |
+
|
| 292 |
+
data/train-00007-of-00036.parquet: 9%|β | 53.2M/618M [00:01<00:10, 53.2MB/s][A
|
| 293 |
+
|
| 294 |
+
data/train-00007-of-00036.parquet: 75%|ββββββββ | 467M/618M [00:02<00:00, 262MB/s] [A
|
| 295 |
+
data/train-00007-of-00036.parquet: 100%|ββββββββββ| 618M/618M [00:03<00:00, 189MB/s]
|
| 296 |
+
|
| 297 |
+
Downloading data: 22%|βββ | 8/36 [00:23<01:22, 2.96s/files]02/07/2026 05:57:51 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/datasets/rahul7star/hindi-speech-dataset/resolve/0bfd5e2e4555ec80d7dd74b10442836d2e169be6/data/train-00008-of-00036.parquet "HTTP/1.1 302 Found"
|
| 298 |
+
|
| 299 |
+
|
| 300 |
+
data/train-00008-of-00036.parquet: 0%| | 0.00/415M [00:00<?, ?B/s][A
|
| 301 |
+
|
| 302 |
+
data/train-00008-of-00036.parquet: 9%|β | 37.3M/415M [00:01<00:10, 37.2MB/s][A
|
| 303 |
+
data/train-00008-of-00036.parquet: 100%|ββββββββββ| 415M/415M [00:01<00:00, 228MB/s]
|
| 304 |
+
|
| 305 |
+
Downloading data: 25%|βββ | 9/36 [00:24<01:10, 2.61s/files]02/07/2026 05:57:53 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/datasets/rahul7star/hindi-speech-dataset/resolve/0bfd5e2e4555ec80d7dd74b10442836d2e169be6/data/train-00009-of-00036.parquet "HTTP/1.1 302 Found"
|
| 306 |
+
|
| 307 |
+
|
| 308 |
+
data/train-00009-of-00036.parquet: 0%| | 0.00/303M [00:00<?, ?B/s][A
|
| 309 |
+
|
| 310 |
+
data/train-00009-of-00036.parquet: 13%|ββ | 38.1M/303M [00:01<00:06, 38.0MB/s][A
|
| 311 |
+
data/train-00009-of-00036.parquet: 100%|ββββββββββ| 303M/303M [00:01<00:00, 214MB/s]
|
| 312 |
+
|
| 313 |
+
Downloading data: 28%|βββ | 10/36 [00:26<00:58, 2.25s/files]02/07/2026 05:57:54 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/datasets/rahul7star/hindi-speech-dataset/resolve/0bfd5e2e4555ec80d7dd74b10442836d2e169be6/data/train-00010-of-00036.parquet "HTTP/1.1 302 Found"
|
| 314 |
+
|
| 315 |
+
|
| 316 |
+
data/train-00010-of-00036.parquet: 0%| | 0.00/341M [00:00<?, ?B/s][A
|
| 317 |
+
|
| 318 |
+
data/train-00010-of-00036.parquet: 39%|ββββ | 132M/341M [00:01<00:01, 131MB/s][A
|
| 319 |
+
data/train-00010-of-00036.parquet: 100%|ββββββββββ| 341M/341M [00:01<00:00, 179MB/s]
|
| 320 |
+
|
| 321 |
+
Downloading data: 31%|βββ | 11/36 [00:28<00:53, 2.15s/files]02/07/2026 05:57:56 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/datasets/rahul7star/hindi-speech-dataset/resolve/0bfd5e2e4555ec80d7dd74b10442836d2e169be6/data/train-00011-of-00036.parquet "HTTP/1.1 302 Found"
|
| 322 |
+
|
| 323 |
+
|
| 324 |
+
data/train-00011-of-00036.parquet: 0%| | 0.00/440M [00:00<?, ?B/s][A
|
| 325 |
+
|
| 326 |
+
data/train-00011-of-00036.parquet: 9%|β | 41.2M/440M [00:01<00:09, 41.1MB/s][A
|
| 327 |
+
data/train-00011-of-00036.parquet: 100%|ββββββββββ| 440M/440M [00:01<00:00, 255MB/s]
|
| 328 |
+
|
| 329 |
+
Downloading data: 33%|ββββ | 12/36 [00:30<00:48, 2.03s/files]02/07/2026 05:57:58 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/datasets/rahul7star/hindi-speech-dataset/resolve/0bfd5e2e4555ec80d7dd74b10442836d2e169be6/data/train-00012-of-00036.parquet "HTTP/1.1 302 Found"
|
| 330 |
+
|
| 331 |
+
|
| 332 |
+
data/train-00012-of-00036.parquet: 0%| | 0.00/412M [00:00<?, ?B/s][A
|
| 333 |
+
|
| 334 |
+
data/train-00012-of-00036.parquet: 10%|β | 42.4M/412M [00:01<00:08, 42.3MB/s][A
|
| 335 |
+
data/train-00012-of-00036.parquet: 100%|ββββββββββ| 412M/412M [00:01<00:00, 243MB/s]
|
| 336 |
+
|
| 337 |
+
Downloading data: 36%|ββββ | 13/36 [00:31<00:44, 1.93s/files]02/07/2026 05:58:00 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/datasets/rahul7star/hindi-speech-dataset/resolve/0bfd5e2e4555ec80d7dd74b10442836d2e169be6/data/train-00013-of-00036.parquet "HTTP/1.1 302 Found"
|
| 338 |
+
|
| 339 |
+
|
| 340 |
+
data/train-00013-of-00036.parquet: 0%| | 0.00/397M [00:00<?, ?B/s][A
|
| 341 |
+
|
| 342 |
+
data/train-00013-of-00036.parquet: 11%|ββ | 44.8M/397M [00:01<00:07, 44.5MB/s][A
|
| 343 |
+
data/train-00013-of-00036.parquet: 100%|ββββββββββ| 397M/397M [00:01<00:00, 229MB/s]
|
| 344 |
+
|
| 345 |
+
Downloading data: 39%|ββββ | 14/36 [00:33<00:41, 1.88s/files]02/07/2026 05:58:02 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/datasets/rahul7star/hindi-speech-dataset/resolve/0bfd5e2e4555ec80d7dd74b10442836d2e169be6/data/train-00014-of-00036.parquet "HTTP/1.1 302 Found"
|
| 346 |
+
|
| 347 |
+
|
| 348 |
+
data/train-00014-of-00036.parquet: 0%| | 0.00/397M [00:00<?, ?B/s][A
|
| 349 |
+
|
| 350 |
+
data/train-00014-of-00036.parquet: 11%|ββ | 45.7M/397M [00:01<00:07, 45.7MB/s][A
|
| 351 |
+
|
| 352 |
+
data/train-00014-of-00036.parquet: 100%|ββββββββββ| 397M/397M [00:02<00:00, 202MB/s] [A
|
| 353 |
+
data/train-00014-of-00036.parquet: 100%|ββββββββββ| 397M/397M [00:02<00:00, 180MB/s]
|
| 354 |
+
|
| 355 |
+
Downloading data: 42%|βββββ | 15/36 [00:35<00:41, 1.98s/files]02/07/2026 05:58:04 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/datasets/rahul7star/hindi-speech-dataset/resolve/0bfd5e2e4555ec80d7dd74b10442836d2e169be6/data/train-00015-of-00036.parquet "HTTP/1.1 302 Found"
|
| 356 |
+
|
| 357 |
+
|
| 358 |
+
data/train-00015-of-00036.parquet: 0%| | 0.00/389M [00:00<?, ?B/s][A
|
| 359 |
+
|
| 360 |
+
data/train-00015-of-00036.parquet: 9%|β | 34.5M/389M [00:01<00:10, 34.5MB/s][A
|
| 361 |
+
|
| 362 |
+
data/train-00015-of-00036.parquet: 100%|ββββββββββ| 389M/389M [00:02<00:00, 208MB/s] [A
|
| 363 |
+
data/train-00015-of-00036.parquet: 100%|ββββββββββ| 389M/389M [00:02<00:00, 184MB/s]
|
| 364 |
+
|
| 365 |
+
Downloading data: 44%|βββββ | 16/36 [00:37<00:40, 2.03s/files]02/07/2026 05:58:06 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/datasets/rahul7star/hindi-speech-dataset/resolve/0bfd5e2e4555ec80d7dd74b10442836d2e169be6/data/train-00016-of-00036.parquet "HTTP/1.1 302 Found"
|
| 366 |
+
|
| 367 |
+
|
| 368 |
+
data/train-00016-of-00036.parquet: 0%| | 0.00/384M [00:00<?, ?B/s][A
|
| 369 |
+
|
| 370 |
+
data/train-00016-of-00036.parquet: 7%|β | 25.6M/384M [00:01<00:14, 25.5MB/s][A
|
| 371 |
+
data/train-00016-of-00036.parquet: 100%|ββββββββββ| 384M/384M [00:01<00:00, 199MB/s]
|
| 372 |
+
|
| 373 |
+
Downloading data: 47%|βββββ | 17/36 [00:39<00:38, 2.01s/files]02/07/2026 05:58:08 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/datasets/rahul7star/hindi-speech-dataset/resolve/0bfd5e2e4555ec80d7dd74b10442836d2e169be6/data/train-00017-of-00036.parquet "HTTP/1.1 302 Found"
|
| 374 |
+
|
| 375 |
+
|
| 376 |
+
data/train-00017-of-00036.parquet: 0%| | 0.00/441M [00:00<?, ?B/s][A
|
| 377 |
+
|
| 378 |
+
data/train-00017-of-00036.parquet: 6%|β | 28.1M/441M [00:01<00:14, 28.1MB/s][A
|
| 379 |
+
|
| 380 |
+
data/train-00017-of-00036.parquet: 100%|ββββββββββ| 441M/441M [00:02<00:00, 224MB/s] [A
|
| 381 |
+
data/train-00017-of-00036.parquet: 100%|ββββββββββ| 441M/441M [00:02<00:00, 197MB/s]
|
| 382 |
+
|
| 383 |
+
Downloading data: 50%|βββββ | 18/36 [00:42<00:37, 2.08s/files]02/07/2026 05:58:10 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/datasets/rahul7star/hindi-speech-dataset/resolve/0bfd5e2e4555ec80d7dd74b10442836d2e169be6/data/train-00018-of-00036.parquet "HTTP/1.1 302 Found"
|
| 384 |
+
|
| 385 |
+
|
| 386 |
+
data/train-00018-of-00036.parquet: 0%| | 0.00/571M [00:00<?, ?B/s][A
|
| 387 |
+
|
| 388 |
+
data/train-00018-of-00036.parquet: 7%|β | 38.1M/571M [00:01<00:13, 38.1MB/s][A
|
| 389 |
+
|
| 390 |
+
data/train-00018-of-00036.parquet: 79%|ββββββββ | 451M/571M [00:02<00:00, 258MB/s] [A
|
| 391 |
+
data/train-00018-of-00036.parquet: 100%|ββββββββββ| 571M/571M [00:02<00:00, 216MB/s]
|
| 392 |
+
|
| 393 |
+
Downloading data: 53%|ββββββ | 19/36 [00:44<00:38, 2.25s/files]02/07/2026 05:58:13 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/datasets/rahul7star/hindi-speech-dataset/resolve/0bfd5e2e4555ec80d7dd74b10442836d2e169be6/data/train-00019-of-00036.parquet "HTTP/1.1 302 Found"
|
| 394 |
+
|
| 395 |
+
|
| 396 |
+
data/train-00019-of-00036.parquet: 0%| | 0.00/413M [00:00<?, ?B/s][A
|
| 397 |
+
|
| 398 |
+
data/train-00019-of-00036.parquet: 11%|β | 44.7M/413M [00:01<00:08, 44.7MB/s][A
|
| 399 |
+
data/train-00019-of-00036.parquet: 100%|ββββββββββ| 413M/413M [00:01<00:00, 212MB/s]
|
| 400 |
+
|
| 401 |
+
Downloading data: 56%|ββββββ | 20/36 [00:46<00:34, 2.17s/files]02/07/2026 05:58:15 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/datasets/rahul7star/hindi-speech-dataset/resolve/0bfd5e2e4555ec80d7dd74b10442836d2e169be6/data/train-00020-of-00036.parquet "HTTP/1.1 302 Found"
|
| 402 |
+
|
| 403 |
+
|
| 404 |
+
data/train-00020-of-00036.parquet: 0%| | 0.00/417M [00:00<?, ?B/s][A
|
| 405 |
+
|
| 406 |
+
data/train-00020-of-00036.parquet: 12%|ββ | 49.5M/417M [00:01<00:07, 49.5MB/s][A
|
| 407 |
+
data/train-00020-of-00036.parquet: 100%|ββββββββββ| 417M/417M [00:01<00:00, 239MB/s]
|
| 408 |
+
|
| 409 |
+
Downloading data: 58%|ββββββ | 21/36 [00:48<00:30, 2.05s/files]02/07/2026 05:58:17 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/datasets/rahul7star/hindi-speech-dataset/resolve/0bfd5e2e4555ec80d7dd74b10442836d2e169be6/data/train-00021-of-00036.parquet "HTTP/1.1 302 Found"
|
| 410 |
+
|
| 411 |
+
|
| 412 |
+
data/train-00021-of-00036.parquet: 0%| | 0.00/401M [00:00<?, ?B/s][A
|
| 413 |
+
|
| 414 |
+
data/train-00021-of-00036.parquet: 12%|ββ | 47.6M/401M [00:01<00:07, 47.5MB/s][A
|
| 415 |
+
data/train-00021-of-00036.parquet: 100%|ββββββββββ| 401M/401M [00:01<00:00, 209MB/s]
|
| 416 |
+
|
| 417 |
+
Downloading data: 61%|ββββββ | 22/36 [00:50<00:28, 2.02s/files]02/07/2026 05:58:19 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/datasets/rahul7star/hindi-speech-dataset/resolve/0bfd5e2e4555ec80d7dd74b10442836d2e169be6/data/train-00022-of-00036.parquet "HTTP/1.1 302 Found"
|
| 418 |
+
|
| 419 |
+
|
| 420 |
+
data/train-00022-of-00036.parquet: 0%| | 0.00/373M [00:00<?, ?B/s][A
|
| 421 |
+
|
| 422 |
+
data/train-00022-of-00036.parquet: 10%|β | 38.6M/373M [00:01<00:08, 38.6MB/s][A
|
| 423 |
+
data/train-00022-of-00036.parquet: 100%|ββββββββββ| 373M/373M [00:01<00:00, 223MB/s]
|
| 424 |
+
|
| 425 |
+
Downloading data: 64%|βββββββ | 23/36 [00:52<00:24, 1.92s/files]02/07/2026 05:58:20 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/datasets/rahul7star/hindi-speech-dataset/resolve/0bfd5e2e4555ec80d7dd74b10442836d2e169be6/data/train-00023-of-00036.parquet "HTTP/1.1 302 Found"
|
| 426 |
+
|
| 427 |
+
|
| 428 |
+
data/train-00023-of-00036.parquet: 0%| | 0.00/374M [00:00<?, ?B/s][A
|
| 429 |
+
|
| 430 |
+
data/train-00023-of-00036.parquet: 4%|β | 14.1M/374M [00:01<00:25, 14.1MB/s][A
|
| 431 |
+
|
| 432 |
+
data/train-00023-of-00036.parquet: 100%|ββββββββββ| 374M/374M [00:02<00:00, 208MB/s] [A
|
| 433 |
+
data/train-00023-of-00036.parquet: 100%|ββββββββββ| 374M/374M [00:02<00:00, 180MB/s]
|
| 434 |
+
|
| 435 |
+
Downloading data: 67%|βββββββ | 24/36 [00:54<00:23, 1.98s/files]02/07/2026 05:58:22 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/datasets/rahul7star/hindi-speech-dataset/resolve/0bfd5e2e4555ec80d7dd74b10442836d2e169be6/data/train-00024-of-00036.parquet "HTTP/1.1 302 Found"
|
| 436 |
+
|
| 437 |
+
|
| 438 |
+
data/train-00024-of-00036.parquet: 0%| | 0.00/531M [00:00<?, ?B/s][A
|
| 439 |
+
|
| 440 |
+
data/train-00024-of-00036.parquet: 5%|β | 24.3M/531M [00:01<00:20, 24.3MB/s][A
|
| 441 |
+
|
| 442 |
+
data/train-00024-of-00036.parquet: 100%|ββββββββββ| 531M/531M [00:02<00:00, 259MB/s] [A
|
| 443 |
+
data/train-00024-of-00036.parquet: 100%|ββββββββββ| 531M/531M [00:02<00:00, 229MB/s]
|
| 444 |
+
|
| 445 |
+
Downloading data: 69%|βββββββ | 25/36 [00:56<00:22, 2.09s/files]02/07/2026 05:58:25 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/datasets/rahul7star/hindi-speech-dataset/resolve/0bfd5e2e4555ec80d7dd74b10442836d2e169be6/data/train-00025-of-00036.parquet "HTTP/1.1 302 Found"
|
| 446 |
+
|
| 447 |
+
|
| 448 |
+
data/train-00025-of-00036.parquet: 0%| | 0.00/542M [00:00<?, ?B/s][A
|
| 449 |
+
|
| 450 |
+
data/train-00025-of-00036.parquet: 6%|β | 30.3M/542M [00:01<00:17, 30.0MB/s][A
|
| 451 |
+
|
| 452 |
+
data/train-00025-of-00036.parquet: 100%|ββββββββββ| 542M/542M [00:02<00:00, 248MB/s] [A
|
| 453 |
+
data/train-00025-of-00036.parquet: 100%|ββββββββββ| 542M/542M [00:02<00:00, 221MB/s]
|
| 454 |
+
|
| 455 |
+
Downloading data: 72%|ββββββββ | 26/36 [00:59<00:22, 2.21s/files]02/07/2026 05:58:27 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/datasets/rahul7star/hindi-speech-dataset/resolve/0bfd5e2e4555ec80d7dd74b10442836d2e169be6/data/train-00026-of-00036.parquet "HTTP/1.1 302 Found"
|
| 456 |
+
|
| 457 |
+
|
| 458 |
+
data/train-00026-of-00036.parquet: 0%| | 0.00/434M [00:00<?, ?B/s][A
|
| 459 |
+
|
| 460 |
+
data/train-00026-of-00036.parquet: 7%|β | 29.5M/434M [00:01<00:13, 29.4MB/s][A
|
| 461 |
+
|
| 462 |
+
data/train-00026-of-00036.parquet: 100%|ββββββββββ| 434M/434M [00:02<00:00, 234MB/s] [A
|
| 463 |
+
data/train-00026-of-00036.parquet: 100%|ββββββββββ| 434M/434M [00:02<00:00, 205MB/s]
|
| 464 |
+
|
| 465 |
+
Downloading data: 75%|ββββββββ | 27/36 [01:01<00:19, 2.19s/files]02/07/2026 05:58:29 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/datasets/rahul7star/hindi-speech-dataset/resolve/0bfd5e2e4555ec80d7dd74b10442836d2e169be6/data/train-00027-of-00036.parquet "HTTP/1.1 302 Found"
|
| 466 |
+
|
| 467 |
+
|
| 468 |
+
data/train-00027-of-00036.parquet: 0%| | 0.00/366M [00:00<?, ?B/s][A
|
| 469 |
+
|
| 470 |
+
data/train-00027-of-00036.parquet: 9%|β | 33.0M/366M [00:01<00:10, 32.9MB/s][A
|
| 471 |
+
data/train-00027-of-00036.parquet: 100%|ββββββββββ| 366M/366M [00:01<00:00, 197MB/s]
|
| 472 |
+
|
| 473 |
+
Downloading data: 78%|ββββββββ | 28/36 [01:03<00:16, 2.10s/files]02/07/2026 05:58:31 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/datasets/rahul7star/hindi-speech-dataset/resolve/0bfd5e2e4555ec80d7dd74b10442836d2e169be6/data/train-00028-of-00036.parquet "HTTP/1.1 302 Found"
|
| 474 |
+
|
| 475 |
+
|
| 476 |
+
data/train-00028-of-00036.parquet: 0%| | 0.00/374M [00:00<?, ?B/s][A
|
| 477 |
+
|
| 478 |
+
data/train-00028-of-00036.parquet: 4%|β | 13.7M/374M [00:01<00:26, 13.7MB/s][A
|
| 479 |
+
data/train-00028-of-00036.parquet: 100%|ββββββββββ| 374M/374M [00:01<00:00, 199MB/s]
|
| 480 |
+
|
| 481 |
+
Downloading data: 81%|ββββββββ | 29/36 [01:05<00:14, 2.04s/files]02/07/2026 05:58:33 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/datasets/rahul7star/hindi-speech-dataset/resolve/0bfd5e2e4555ec80d7dd74b10442836d2e169be6/data/train-00029-of-00036.parquet "HTTP/1.1 302 Found"
|
| 482 |
+
|
| 483 |
+
|
| 484 |
+
data/train-00029-of-00036.parquet: 0%| | 0.00/402M [00:00<?, ?B/s][A
|
| 485 |
+
|
| 486 |
+
data/train-00029-of-00036.parquet: 12%|ββ | 48.8M/402M [00:01<00:07, 48.7MB/s][A
|
| 487 |
+
data/train-00029-of-00036.parquet: 100%|ββββββββββ| 402M/402M [00:01<00:00, 252MB/s]
|
| 488 |
+
|
| 489 |
+
Downloading data: 83%|βββββββββ | 30/36 [01:06<00:11, 1.92s/files]02/07/2026 05:58:35 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/datasets/rahul7star/hindi-speech-dataset/resolve/0bfd5e2e4555ec80d7dd74b10442836d2e169be6/data/train-00030-of-00036.parquet "HTTP/1.1 302 Found"
|
| 490 |
+
|
| 491 |
+
|
| 492 |
+
data/train-00030-of-00036.parquet: 0%| | 0.00/400M [00:00<?, ?B/s][A
|
| 493 |
+
|
| 494 |
+
data/train-00030-of-00036.parquet: 2%|β | 9.23M/400M [00:01<00:42, 9.23MB/s][A
|
| 495 |
+
|
| 496 |
+
data/train-00030-of-00036.parquet: 100%|ββββββββββ| 400M/400M [00:02<00:00, 222MB/s] [A
|
| 497 |
+
data/train-00030-of-00036.parquet: 100%|ββββββββββ| 400M/400M [00:02<00:00, 192MB/s]
|
| 498 |
+
|
| 499 |
+
Downloading data: 86%|βββββββββ | 31/36 [01:08<00:09, 1.97s/files]02/07/2026 05:58:37 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/datasets/rahul7star/hindi-speech-dataset/resolve/0bfd5e2e4555ec80d7dd74b10442836d2e169be6/data/train-00031-of-00036.parquet "HTTP/1.1 302 Found"
|
| 500 |
+
|
| 501 |
+
|
| 502 |
+
data/train-00031-of-00036.parquet: 0%| | 0.00/382M [00:00<?, ?B/s][A
|
| 503 |
+
|
| 504 |
+
data/train-00031-of-00036.parquet: 9%|β | 33.4M/382M [00:01<00:10, 33.3MB/s][A
|
| 505 |
+
data/train-00031-of-00036.parquet: 100%|ββββββββββ| 382M/382M [00:01<00:00, 233MB/s]
|
| 506 |
+
|
| 507 |
+
Downloading data: 89%|βββββββββ | 32/36 [01:10<00:07, 1.88s/files]02/07/2026 05:58:38 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/datasets/rahul7star/hindi-speech-dataset/resolve/0bfd5e2e4555ec80d7dd74b10442836d2e169be6/data/train-00032-of-00036.parquet "HTTP/1.1 302 Found"
|
| 508 |
+
|
| 509 |
+
|
| 510 |
+
data/train-00032-of-00036.parquet: 0%| | 0.00/380M [00:00<?, ?B/s][A
|
| 511 |
+
|
| 512 |
+
data/train-00032-of-00036.parquet: 6%|β | 22.8M/380M [00:01<00:15, 22.7MB/s][A
|
| 513 |
+
|
| 514 |
+
data/train-00032-of-00036.parquet: 100%|ββββββββββ| 380M/380M [00:02<00:00, 216MB/s] [A
|
| 515 |
+
data/train-00032-of-00036.parquet: 100%|ββββββββββ| 380M/380M [00:02<00:00, 187MB/s]
|
| 516 |
+
|
| 517 |
+
Downloading data: 92%|ββββββββββ| 33/36 [01:12<00:05, 1.93s/files]02/07/2026 05:58:41 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/datasets/rahul7star/hindi-speech-dataset/resolve/0bfd5e2e4555ec80d7dd74b10442836d2e169be6/data/train-00033-of-00036.parquet "HTTP/1.1 302 Found"
|
| 518 |
+
|
| 519 |
+
|
| 520 |
+
data/train-00033-of-00036.parquet: 0%| | 0.00/376M [00:00<?, ?B/s][A
|
| 521 |
+
|
| 522 |
+
data/train-00033-of-00036.parquet: 11%|β | 41.4M/376M [00:01<00:08, 41.4MB/s][A
|
| 523 |
+
data/train-00033-of-00036.parquet: 100%|ββββββββββ| 376M/376M [00:01<00:00, 232MB/s]
|
| 524 |
+
|
| 525 |
+
Downloading data: 94%|ββββββββββ| 34/36 [01:14<00:03, 1.84s/files]02/07/2026 05:58:42 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/datasets/rahul7star/hindi-speech-dataset/resolve/0bfd5e2e4555ec80d7dd74b10442836d2e169be6/data/train-00034-of-00036.parquet "HTTP/1.1 302 Found"
|
| 526 |
+
|
| 527 |
+
|
| 528 |
+
data/train-00034-of-00036.parquet: 0%| | 0.00/372M [00:00<?, ?B/s][A
|
| 529 |
+
|
| 530 |
+
data/train-00034-of-00036.parquet: 11%|β | 40.0M/372M [00:01<00:08, 39.9MB/s][A
|
| 531 |
+
data/train-00034-of-00036.parquet: 100%|ββββββββββ| 372M/372M [00:01<00:00, 228MB/s]
|
| 532 |
+
|
| 533 |
+
Downloading data: 97%|ββββββββββ| 35/36 [01:15<00:01, 1.78s/files]02/07/2026 05:58:44 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/datasets/rahul7star/hindi-speech-dataset/resolve/0bfd5e2e4555ec80d7dd74b10442836d2e169be6/data/train-00035-of-00036.parquet "HTTP/1.1 302 Found"
|
| 534 |
+
|
| 535 |
+
|
| 536 |
+
data/train-00035-of-00036.parquet: 0%| | 0.00/373M [00:00<?, ?B/s][A
|
| 537 |
+
|
| 538 |
+
data/train-00035-of-00036.parquet: 8%|β | 31.4M/373M [00:01<00:10, 31.3MB/s][A
|
| 539 |
+
data/train-00035-of-00036.parquet: 100%|ββββββββββ| 373M/373M [00:01<00:00, 230MB/s]
|
| 540 |
+
|
| 541 |
+
Downloading data: 100%|ββββββββββ| 36/36 [01:17<00:00, 1.74s/files]
|
| 542 |
+
Downloading data: 100%|ββββββββββ| 36/36 [01:17<00:00, 2.15s/files]
|
| 543 |
+
02/07/2026 05:58:45 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/datasets/rahul7star/hindi-speech-dataset/resolve/0bfd5e2e4555ec80d7dd74b10442836d2e169be6/data/validation-00000-of-00001.parquet "HTTP/1.1 302 Found"
|
| 544 |
+
|
| 545 |
+
|
| 546 |
+
data/validation-00000-of-00001.parquet: 0%| | 0.00/162M [00:00<?, ?B/s][A
|
| 547 |
+
data/validation-00000-of-00001.parquet: 100%|ββββββββββ| 162M/162M [00:00<00:00, 175MB/s]
|
| 548 |
+
02/07/2026 05:58:47 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/datasets/rahul7star/hindi-speech-dataset/resolve/0bfd5e2e4555ec80d7dd74b10442836d2e169be6/data/test-00000-of-00001.parquet "HTTP/1.1 302 Found"
|
| 549 |
+
|
| 550 |
+
|
| 551 |
+
data/test-00000-of-00001.parquet: 0%| | 0.00/306M [00:00<?, ?B/s][A
|
| 552 |
+
|
| 553 |
+
data/test-00000-of-00001.parquet: 10%|β | 29.9M/306M [00:01<00:09, 29.9MB/s][A
|
| 554 |
+
data/test-00000-of-00001.parquet: 100%|ββββββββββ| 306M/306M [00:01<00:00, 178MB/s]
|
| 555 |
+
|
| 556 |
+
|
| 557 |
+
Generating train split: 0%| | 0/145152 [00:00<?, ? examples/s][A
|
| 558 |
+
|
| 559 |
+
Generating train split: 0%| | 200/145152 [00:01<16:16, 148.41 examples/s][A
|
| 560 |
+
|
| 561 |
+
Generating train split: 0%| | 500/145152 [00:02<11:27, 210.32 examples/s][A
|
| 562 |
+
|
| 563 |
+
Generating train split: 1%| | 800/145152 [00:03<10:39, 225.65 examples/s][A
|
| 564 |
+
|
| 565 |
+
Generating train split: 1%| | 1100/145152 [00:05<10:30, 228.51 examples/s][A
|
| 566 |
+
|
| 567 |
+
Generating train split: 1%| | 1400/145152 [00:06<09:54, 241.88 examples/s][A
|
| 568 |
+
|
| 569 |
+
Generating train split: 1%| | 1700/145152 [00:07<09:38, 248.09 examples/s][A
|
| 570 |
+
|
| 571 |
+
Generating train split: 1%|β | 2000/145152 [00:08<09:38, 247.57 examples/s][A
|
| 572 |
+
|
| 573 |
+
Generating train split: 3%|β | 4132/145152 [00:09<03:06, 755.90 examples/s][A
|
| 574 |
+
|
| 575 |
+
Generating train split: 4%|β | 6232/145152 [00:10<02:02, 1131.53 examples/s][A
|
| 576 |
+
|
| 577 |
+
Generating train split: 6%|β | 8464/145152 [00:11<01:36, 1417.27 examples/s][A
|
| 578 |
+
|
| 579 |
+
Generating train split: 7%|β | 10664/145152 [00:12<01:22, 1627.59 examples/s][A
|
| 580 |
+
|
| 581 |
+
Generating train split: 9%|β | 13596/145152 [00:13<01:07, 1960.61 examples/s][A
|
| 582 |
+
|
| 583 |
+
Generating train split: 11%|ββ | 16428/145152 [00:14<00:58, 2202.00 examples/s][A
|
| 584 |
+
|
| 585 |
+
Generating train split: 13%|ββ | 19428/145152 [00:15<00:52, 2389.78 examples/s][A
|
| 586 |
+
|
| 587 |
+
Generating train split: 15%|ββ | 21860/145152 [00:17<01:01, 2003.32 examples/s][A
|
| 588 |
+
|
| 589 |
+
Generating train split: 17%|ββ | 24060/145152 [00:19<01:12, 1664.47 examples/s][A
|
| 590 |
+
|
| 591 |
+
Generating train split: 18%|ββ | 25892/145152 [00:20<01:18, 1522.17 examples/s][A
|
| 592 |
+
|
| 593 |
+
Generating train split: 19%|ββ | 27592/145152 [00:22<01:22, 1418.53 examples/s][A
|
| 594 |
+
|
| 595 |
+
Generating train split: 20%|ββ | 29224/145152 [00:23<01:23, 1386.33 examples/s][A
|
| 596 |
+
|
| 597 |
+
Generating train split: 22%|βββ | 31224/145152 [00:24<01:15, 1501.84 examples/s][A
|
| 598 |
+
|
| 599 |
+
Generating train split: 23%|βββ | 33056/145152 [00:25<01:10, 1580.15 examples/s][A
|
| 600 |
+
|
| 601 |
+
Generating train split: 25%|βββ | 35756/145152 [00:26<00:58, 1870.49 examples/s][A
|
| 602 |
+
|
| 603 |
+
Generating train split: 27%|βββ | 39488/145152 [00:27<00:45, 2320.75 examples/s][A
|
| 604 |
+
|
| 605 |
+
Generating train split: 30%|βββ | 43120/145152 [00:28<00:38, 2654.22 examples/s][A
|
| 606 |
+
|
| 607 |
+
Generating train split: 32%|ββββ | 45852/145152 [00:30<00:38, 2584.46 examples/s][A
|
| 608 |
+
|
| 609 |
+
Generating train split: 34%|ββββ | 48684/145152 [00:31<00:37, 2544.79 examples/s][A
|
| 610 |
+
|
| 611 |
+
Generating train split: 35%|ββββ | 51384/145152 [00:32<00:36, 2553.03 examples/s][A
|
| 612 |
+
|
| 613 |
+
Generating train split: 37%|ββββ | 54216/145152 [00:33<00:35, 2583.01 examples/s][A
|
| 614 |
+
|
| 615 |
+
Generating train split: 39%|ββββ | 57048/145152 [00:34<00:33, 2608.58 examples/s][A
|
| 616 |
+
|
| 617 |
+
Generating train split: 41%|βββββ | 60048/145152 [00:35<00:32, 2643.23 examples/s][A
|
| 618 |
+
|
| 619 |
+
Generating train split: 43%|βββββ | 62880/145152 [00:36<00:30, 2692.08 examples/s][A
|
| 620 |
+
|
| 621 |
+
Generating train split: 45%|βββββ | 65712/145152 [00:37<00:29, 2719.25 examples/s][A
|
| 622 |
+
|
| 623 |
+
Generating train split: 47%|βββββ | 68644/145152 [00:38<00:27, 2775.09 examples/s][A
|
| 624 |
+
|
| 625 |
+
Generating train split: 49%|βββββ | 71444/145152 [00:39<00:26, 2745.00 examples/s][A
|
| 626 |
+
|
| 627 |
+
Generating train split: 51%|βββββ | 74376/145152 [00:41<00:29, 2400.59 examples/s][A
|
| 628 |
+
|
| 629 |
+
Generating train split: 53%|ββββββ | 76908/145152 [00:42<00:30, 2240.94 examples/s][A
|
| 630 |
+
|
| 631 |
+
Generating train split: 55%|ββββββ | 79608/145152 [00:43<00:28, 2330.99 examples/s][A
|
| 632 |
+
|
| 633 |
+
Generating train split: 57%|ββββββ | 82440/145152 [00:44<00:26, 2394.60 examples/s][A
|
| 634 |
+
|
| 635 |
+
Generating train split: 59%|ββββββ | 85272/145152 [00:45<00:24, 2451.03 examples/s][A
|
| 636 |
+
|
| 637 |
+
Generating train split: 61%|ββββββ | 87972/145152 [00:46<00:22, 2514.74 examples/s][A
|
| 638 |
+
|
| 639 |
+
Generating train split: 63%|βββββββ | 91104/145152 [00:47<00:20, 2615.73 examples/s][A
|
| 640 |
+
|
| 641 |
+
Generating train split: 65%|βββββββ | 94236/145152 [00:48<00:18, 2680.32 examples/s][A
|
| 642 |
+
|
| 643 |
+
Generating train split: 67%|βββββββ | 97068/145152 [00:49<00:17, 2713.01 examples/s][A
|
| 644 |
+
|
| 645 |
+
Generating train split: 69%|βββββββ | 99868/145152 [00:51<00:18, 2447.66 examples/s][A
|
| 646 |
+
|
| 647 |
+
Generating train split: 71%|βββββββ | 102400/145152 [00:52<00:18, 2291.35 examples/s][A
|
| 648 |
+
|
| 649 |
+
Generating train split: 72%|ββββββββ | 104932/145152 [00:53<00:18, 2200.44 examples/s][A
|
| 650 |
+
|
| 651 |
+
Generating train split: 74%|ββββββββ | 107432/145152 [00:54<00:16, 2220.23 examples/s][A
|
| 652 |
+
|
| 653 |
+
Generating train split: 76%|ββββββββ | 110364/145152 [00:55<00:14, 2402.21 examples/s][A
|
| 654 |
+
|
| 655 |
+
Generating train split: 78%|ββββββββ | 113496/145152 [00:57<00:12, 2556.73 examples/s][A
|
| 656 |
+
|
| 657 |
+
Generating train split: 80%|ββββββββ | 116496/145152 [00:58<00:10, 2644.30 examples/s][A
|
| 658 |
+
|
| 659 |
+
Generating train split: 82%|βββββββββ | 119328/145152 [00:59<00:09, 2662.16 examples/s][A
|
| 660 |
+
|
| 661 |
+
Generating train split: 84%|βββββββββ | 122160/145152 [01:00<00:08, 2664.12 examples/s][A
|
| 662 |
+
|
| 663 |
+
Generating train split: 86%|βββββββββ | 125092/145152 [01:01<00:07, 2701.64 examples/s][A
|
| 664 |
+
|
| 665 |
+
Generating train split: 88%|βββββββββ | 127992/145152 [01:02<00:06, 2713.96 examples/s][A
|
| 666 |
+
|
| 667 |
+
Generating train split: 90%|βββββββββ | 130824/145152 [01:03<00:05, 2743.11 examples/s][A
|
| 668 |
+
|
| 669 |
+
Generating train split: 92%|ββββββββββ| 133956/145152 [01:04<00:04, 2778.09 examples/s][A
|
| 670 |
+
|
| 671 |
+
Generating train split: 95%|ββββββββββ| 137188/145152 [01:05<00:02, 2830.10 examples/s][A
|
| 672 |
+
|
| 673 |
+
Generating train split: 97%|ββββββββββ| 140088/145152 [01:06<00:01, 2838.90 examples/s][A
|
| 674 |
+
|
| 675 |
+
Generating train split: 99%|ββββββββββ| 143220/145152 [01:07<00:00, 2872.01 examples/s][A
|
| 676 |
+
Generating train split: 100%|ββββββββββ| 145152/145152 [01:08<00:00, 2129.23 examples/s]
|
| 677 |
+
|
| 678 |
+
|
| 679 |
+
Generating validation split: 0%| | 0/239 [00:00<?, ? examples/s][A
|
| 680 |
+
Generating validation split: 100%|ββββββββββ| 239/239 [00:00<00:00, 280.23 examples/s]
|
| 681 |
+
|
| 682 |
+
|
| 683 |
+
Generating test split: 0%| | 0/418 [00:00<?, ? examples/s][A
|
| 684 |
+
|
| 685 |
+
Generating test split: 48%|βββββ | 200/418 [00:01<00:01, 166.80 examples/s][A
|
| 686 |
+
Generating test split: 100%|ββββββββββ| 418/418 [00:01<00:00, 254.47 examples/s]
|
| 687 |
+
02/07/2026 05:59:59 - INFO - __main__ - *** Training T3 model ***
|
| 688 |
+
|
| 689 |
+
|
| 690 |
+
0%| | 0/145152 [00:00<?, ?it/s][ATraceback (most recent call last):
|
| 691 |
File "/app/chatterbox-multilingual-finetuning/src/finetune_t3.py", line 849, in <module>
|
| 692 |
main()
|
| 693 |
~~~~^^
|
|
|
|
| 712 |
...<5 lines>...
|
| 713 |
metric_key_prefix=metric_key_prefix,
|
| 714 |
)
|
| 715 |
+
File "/usr/local/lib/python3.13/site-packages/transformers/trainer.py", line 4468, in evaluation_loop
|
| 716 |
+
for step, inputs in enumerate(dataloader):
|
| 717 |
+
~~~~~~~~~^^^^^^^^^^^^
|
| 718 |
+
File "/usr/local/lib/python3.13/site-packages/accelerate/data_loader.py", line 567, in __iter__
|
| 719 |
+
current_batch = next(dataloader_iter)
|
| 720 |
+
File "/usr/local/lib/python3.13/site-packages/torch/utils/data/dataloader.py", line 741, in __next__
|
| 721 |
+
data = self._next_data()
|
| 722 |
+
File "/usr/local/lib/python3.13/site-packages/torch/utils/data/dataloader.py", line 1548, in _next_data
|
| 723 |
+
return self._process_data(data, worker_id)
|
| 724 |
+
~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^
|
| 725 |
+
File "/usr/local/lib/python3.13/site-packages/torch/utils/data/dataloader.py", line 1586, in _process_data
|
| 726 |
+
data.reraise()
|
| 727 |
+
~~~~~~~~~~~~^^
|
| 728 |
+
File "/usr/local/lib/python3.13/site-packages/torch/_utils.py", line 775, in reraise
|
| 729 |
+
raise exception
|
| 730 |
+
KeyError: Caught KeyError in DataLoader worker process 0.
|
| 731 |
+
Original Traceback (most recent call last):
|
| 732 |
+
File "/usr/local/lib/python3.13/site-packages/torch/utils/data/_utils/worker.py", line 358, in _worker_loop
|
| 733 |
+
data = fetcher.fetch(index) # type: ignore[possibly-undefined]
|
| 734 |
+
File "/usr/local/lib/python3.13/site-packages/torch/utils/data/_utils/fetch.py", line 54, in fetch
|
| 735 |
+
data = [self.dataset[idx] for idx in possibly_batched_index]
|
| 736 |
+
~~~~~~~~~~~~^^^^^
|
| 737 |
+
File "/app/chatterbox-multilingual-finetuning/src/finetune_t3.py", line 239, in __getitem__
|
| 738 |
+
wav_16k, text = self._load_audio_text_from_item(idx)
|
| 739 |
+
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^
|
| 740 |
+
File "/app/chatterbox-multilingual-finetuning/src/finetune_t3.py", line 188, in _load_audio_text_from_item
|
| 741 |
+
text = item[self.data_args.text_column_name]
|
| 742 |
+
~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 743 |
+
KeyError: 'text_scribe'
|
| 744 |
+
|
| 745 |
+
|
| 746 |
+
0%| | 0/145152 [00:04<?, ?it/s]
|