Chatterbox fine-tuned model + logs

runs/Feb07_05-31-06_r-rahul7star-chatterbox-train-gfkn44wm-f343a-8jf6z/events.out.tfevents.1770438666.r-rahul7star-chatterbox-train-gfkn44wm-f343a-8jf6z.44.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5faffe1cb2925e0fe23f69c644aa52f0c754d272a5c03b06545c8651e3e66090
+size 4094

training.log

@@ -1,7 +1,8 @@
+loaded PerthNet (Implicit) at step 250,000
 
 /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.
   from pkg_resources import resource_filename
-02/07/2026 05:21:50 - INFO - __main__ - Training/evaluation parameters CustomTrainingArguments(
+02/07/2026 05:27:34 - INFO - __main__ - Training/evaluation parameters CustomTrainingArguments(
 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},
 adam_beta1=0.9,
 adam_beta2=0.999,
@@ -113,123 +114,721 @@ warmup_ratio=None,
 warmup_steps=1.0,
 weight_decay=0.0,
 )
-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)
-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)
-02/07/2026 05:21:50 - INFO - __main__ - Loading ChatterboxTTS model...
-02/07/2026 05:21:50 - INFO - __main__ - Loading model from Hugging Face Hub: ResembleAI/chatterbox
+02/07/2026 05:27:34 - 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)
+02/07/2026 05:27:34 - 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)
+02/07/2026 05:27:34 - INFO - __main__ - Loading ChatterboxTTS model...
+02/07/2026 05:27:34 - INFO - __main__ - Loading model from Hugging Face Hub: ResembleAI/chatterbox
 /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.
   warnings.warn(
-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"
-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"
+02/07/2026 05:27:34 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/ResembleAI/chatterbox/resolve/main/ve.safetensors "HTTP/1.1 302 Found"
+02/07/2026 05:27:34 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/models/ResembleAI/chatterbox/xet-read-token/05e904af2b5c7f8e482687a9d7336c5c824467d9 "HTTP/1.1 200 OK"
 
 
 ve.safetensors:   0%|          | 0.00/5.70M [00:00<?, ?B/s]
-ve.safetensors: 100%|██████████| 5.70M/5.70M [00:00<00:00, 21.5MB/s]
-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"
+ve.safetensors: 100%|██████████| 5.70M/5.70M [00:00<00:00, 25.1MB/s]
+02/07/2026 05:27:34 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/ResembleAI/chatterbox/resolve/main/t3_mtl23ls_v2.safetensors "HTTP/1.1 302 Found"
 
 
 t3_mtl23ls_v2.safetensors:   0%|          | 0.00/2.14G [00:00<?, ?B/s]
 
-t3_mtl23ls_v2.safetensors:   0%|          | 7.60M/2.14G [00:01<05:35, 6.37MB/s]
+t3_mtl23ls_v2.safetensors:   0%|          | 7.60M/2.14G [00:01<07:01, 5.06MB/s]
 
-t3_mtl23ls_v2.safetensors:   4%|▎         | 78.6M/2.14G [00:04<01:49, 18.9MB/s]
+t3_mtl23ls_v2.safetensors:   4%|▎         | 78.8M/2.14G [00:08<03:32, 9.73MB/s]
 
-t3_mtl23ls_v2.safetensors:  27%|██▋       | 576M/2.14G [00:06<00:15, 102MB/s]  
+t3_mtl23ls_v2.safetensors:  43%|████▎     | 932M/2.14G [00:09<00:08, 139MB/s]  
 
-t3_mtl23ls_v2.safetensors:  34%|███▎      | 719M/2.14G [00:08<00:14, 97.7MB/s]
-
-t3_mtl23ls_v2.safetensors:  67%|██████▋   | 1.43G/2.14G [00:09<00:03, 224MB/s]
-t3_mtl23ls_v2.safetensors: 100%|██████████| 2.14G/2.14G [00:10<00:00, 207MB/s]
-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"
+t3_mtl23ls_v2.safetensors:  80%|████████  | 1.72G/2.14G [00:10<00:01, 254MB/s]
+t3_mtl23ls_v2.safetensors: 100%|██████████| 2.14G/2.14G [00:10<00:00, 202MB/s]
+02/07/2026 05:27:45 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/ResembleAI/chatterbox/resolve/main/s3gen.safetensors "HTTP/1.1 302 Found"
 
 
 s3gen.safetensors:   0%|          | 0.00/1.06G [00:00<?, ?B/s]
 
-s3gen.safetensors:   5%|▍         | 50.7M/1.06G [00:01<00:34, 29.2MB/s]
+s3gen.safetensors:   6%|▋         | 67.0M/1.06G [00:01<00:24, 40.1MB/s]
 
-s3gen.safetensors:  30%|███       | 319M/1.06G [00:02<00:05, 137MB/s]  
-s3gen.safetensors: 100%|██████████| 1.06G/1.06G [00:03<00:00, 335MB/s]
-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"
-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"
-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"
+s3gen.safetensors:  38%|███▊      | 402M/1.06G [00:02<00:03, 172MB/s]  
+s3gen.safetensors: 100%|██████████| 1.06G/1.06G [00:03<00:00, 316MB/s]
+02/07/2026 05:27:48 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/ResembleAI/chatterbox/resolve/main/mtl_tokenizer.json "HTTP/1.1 307 Temporary Redirect"
+02/07/2026 05:27:48 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/api/resolve-cache/models/ResembleAI/chatterbox/05e904af2b5c7f8e482687a9d7336c5c824467d9/mtl_tokenizer.json "HTTP/1.1 200 OK"
+02/07/2026 05:27:48 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/resolve-cache/models/ResembleAI/chatterbox/05e904af2b5c7f8e482687a9d7336c5c824467d9/mtl_tokenizer.json "HTTP/1.1 200 OK"
 
 
 mtl_tokenizer.json:   0%|          | 0.00/68.1k [00:00<?, ?B/s]
-mtl_tokenizer.json: 100%|██████████| 68.1k/68.1k [00:00<00:00, 86.5MB/s]
-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"
+mtl_tokenizer.json: 100%|██████████| 68.1k/68.1k [00:00<00:00, 102MB/s]
+02/07/2026 05:27:48 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/ResembleAI/chatterbox/resolve/main/conds.pt "HTTP/1.1 302 Found"
 
 
 conds.pt:   0%|          | 0.00/107k [00:00<?, ?B/s]
-conds.pt: 100%|██████████| 107k/107k [00:00<00:00, 1.14MB/s]
-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"
+conds.pt: 100%|██████████| 107k/107k [00:00<00:00, 1.28MB/s]
+02/07/2026 05:27:48 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/models/ResembleAI/chatterbox/revision/main "HTTP/1.1 200 OK"
 
 
 Downloading (incomplete total...): 0.00B [00:00, ?B/s]
 
-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"
-
+Fetching 5 files:   0%|          | 0/5 [00:00<?, ?it/s]02/07/2026 05:27:48 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/ResembleAI/chatterbox/resolve/05e904af2b5c7f8e482687a9d7336c5c824467d9/conds.pt "HTTP/1.1 302 Found"
 
-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"
-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"
-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"
 
+Downloading (incomplete total...):   0%|          | 0.00/107k [00:00<?, ?B/s]02/07/2026 05:27:48 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/ResembleAI/chatterbox/resolve/05e904af2b5c7f8e482687a9d7336c5c824467d9/t3_mtl23ls_v2.safetensors "HTTP/1.1 302 Found"
+02/07/2026 05:27:48 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/ResembleAI/chatterbox/resolve/05e904af2b5c7f8e482687a9d7336c5c824467d9/ve.pt "HTTP/1.1 302 Found"
 
-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"
+02/07/2026 05:27:48 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/ResembleAI/chatterbox/resolve/05e904af2b5c7f8e482687a9d7336c5c824467d9/s3gen.pt "HTTP/1.1 302 Found"
 
+Downloading (incomplete total...):   0%|          | 0.00/2.15G [00:00<?, ?B/s]
 
-Downloading (incomplete total...):   0%|          | 0.00/3.20G [00:00<?, ?B/s]
+Downloading (incomplete total...):   0%|          | 0.00/2.15G [00:00<?, ?B/s]
 
-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"
-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"
+Downloading (incomplete total...):   0%|          | 0.00/3.21G [00:00<?, ?B/s]02/07/2026 05:27:48 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/ResembleAI/chatterbox/resolve/05e904af2b5c7f8e482687a9d7336c5c824467d9/grapheme_mtl_merged_expanded_v1.json "HTTP/1.1 307 Temporary Redirect"
+02/07/2026 05:27:48 - 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"
+02/07/2026 05:27:48 - 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"
 
 
 Downloading (incomplete total...):   0%|          | 0.00/3.21G [00:00<?, ?B/s]
 
-Downloading (incomplete total...):   0%|          | 13.5M/3.21G [00:02<10:16, 5.18MB/s]
+Downloading (incomplete total...):   0%|          | 13.5M/3.21G [00:03<12:42, 4.19MB/s]
+
+Downloading (incomplete total...):   5%|▍         | 148M/3.21G [00:05<01:38, 31.0MB/s] 
 
-Downloading (incomplete total...):   4%|▍         | 136M/3.21G [00:04<01:31, 33.7MB/s] 
+Downloading (incomplete total...):  24%|██▍       | 768M/3.21G [00:06<00:14, 168MB/s] 
 
-Downloading (incomplete total...):  13%|█▎        | 412M/3.21G [00:05<00:28, 97.6MB/s]
+Downloading (incomplete total...):  34%|███▍      | 1.10G/3.21G [00:11<00:19, 106MB/s]
 
-Downloading (incomplete total...):  28%|██▊       | 894M/3.21G [00:08<00:17, 135MB/s] 
+Fetching 5 files:  60%|██████    | 3/5 [00:11<00:07,  3.98s/it]
 
-Downloading (incomplete total...):  34%|███▍      | 1.10G/3.21G [00:11<00:20, 103MB/s]
+Downloading (incomplete total...):  49%|████▉     | 1.57G/3.21G [00:12<00:10, 159MB/s]
 
-Downloading (incomplete total...):  67%|██████▋   | 2.14G/3.21G [00:12<00:04, 259MB/s]
+Downloading (incomplete total...): 100%|██████████| 3.21G/3.21G [00:13<00:00, 420MB/s]
 
-Fetching 5 files:  60%|██████    | 3/5 [00:13<00:08,  4.46s/it]
-Fetching 5 files: 100%|██████████| 5/5 [00:13<00:00,  2.68s/it]
+Fetching 5 files:  80%|████████  | 4/5 [00:13<00:03,  3.25s/it]
+Fetching 5 files: 100%|██████████| 5/5 [00:13<00:00,  2.73s/it]
 
 
-Download complete: 100%|██████████| 3.21G/3.21G [00:13<00:00, 259MB/s]                
-Download complete: 100%|██████████| 3.21G/3.21G [00:22<00:00, 140MB/s]
+Download complete: 100%|██████████| 3.21G/3.21G [00:13<00:00, 420MB/s]                
+Download complete: 100%|██████████| 3.21G/3.21G [00:21<00:00, 146MB/s]
 /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`.
   deprecate("LoRACompatibleLinear", "1.0.0", deprecation_message)
-02/07/2026 05:22:29 - INFO - root - input frame rate=25
-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"
-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"
-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"
+02/07/2026 05:28:12 - INFO - root - input frame rate=25
+02/07/2026 05:28:14 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/ResembleAI/chatterbox/resolve/main/Cangjie5_TC.json "HTTP/1.1 307 Temporary Redirect"
+02/07/2026 05:28:14 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/api/resolve-cache/models/ResembleAI/chatterbox/05e904af2b5c7f8e482687a9d7336c5c824467d9/Cangjie5_TC.json "HTTP/1.1 200 OK"
+02/07/2026 05:28:14 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/resolve-cache/models/ResembleAI/chatterbox/05e904af2b5c7f8e482687a9d7336c5c824467d9/Cangjie5_TC.json "HTTP/1.1 200 OK"
 
 
 Cangjie5_TC.json:   0%|          | 0.00/1.92M [00:00<?, ?B/s]
-Cangjie5_TC.json: 100%|██████████| 1.92M/1.92M [00:00<00:00, 23.0MB/s]
+Cangjie5_TC.json: 100%|██████████| 1.92M/1.92M [00:00<00:00, 36.6MB/s]
 Downloading: "https://github.com/explosion/spacy-pkuseg/releases/download/v0.0.26/spacy_ontonotes.zip" to /root/.pkuseg/spacy_ontonotes.zip
 
 
   0%|          | 0/34567143 [00:00<?, ?it/s]
-100%|██████████| 34567143/34567143 [00:00<00:00, 159733455.87it/s]
-Traceback (most recent call last):
+100%|██████████| 34567143/34567143 [00:00<00:00, 176772301.39it/s]
+02/07/2026 05:28:16 - INFO - __main__ - Voice Encoder frozen.
+02/07/2026 05:28:16 - INFO - __main__ - S3Gen model frozen.
+02/07/2026 05:28:16 - INFO - __main__ - T3 model set to trainable.
+02/07/2026 05:28:16 - INFO - __main__ - Loading and processing dataset...
+02/07/2026 05:28:16 - INFO - __main__ - Loading dataset 'rahul7star/hindi-speech-dataset' from Hugging Face Hub.
+02/07/2026 05:28:16 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/datasets/rahul7star/hindi-speech-dataset/resolve/main/README.md "HTTP/1.1 307 Temporary Redirect"
+02/07/2026 05:28:16 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/api/resolve-cache/datasets/rahul7star/hindi-speech-dataset/0bfd5e2e4555ec80d7dd74b10442836d2e169be6/README.md "HTTP/1.1 200 OK"
+02/07/2026 05:28:16 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/resolve-cache/datasets/rahul7star/hindi-speech-dataset/0bfd5e2e4555ec80d7dd74b10442836d2e169be6/README.md "HTTP/1.1 200 OK"
+
+
+README.md:   0%|          | 0.00/591 [00:00<?, ?B/s]
+README.md: 100%|██████████| 591/591 [00:00<00:00, 2.06MB/s]
+02/07/2026 05:28:16 - 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"
+02/07/2026 05:28:16 - 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"
+02/07/2026 05:28:17 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/datasets/rahul7star/hindi-speech-dataset/revision/0bfd5e2e4555ec80d7dd74b10442836d2e169be6 "HTTP/1.1 200 OK"
+02/07/2026 05:28:17 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/datasets/rahul7star/hindi-speech-dataset/resolve/0bfd5e2e4555ec80d7dd74b10442836d2e169be6/.huggingface.yaml "HTTP/1.1 404 Not Found"
+02/07/2026 05:28:17 - INFO - httpx - HTTP Request: GET https://datasets-server.huggingface.co/info?dataset=rahul7star/hindi-speech-dataset "HTTP/1.1 200 OK"
+02/07/2026 05:28:17 - 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"
+02/07/2026 05:28:17 - 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"
+02/07/2026 05:28:17 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/datasets/rahul7star/hindi-speech-dataset/resolve/0bfd5e2e4555ec80d7dd74b10442836d2e169be6/dataset_infos.json "HTTP/1.1 404 Not Found"
+
+Downloading data:   0%|          | 0/36 [00:00<?, ?files/s]02/07/2026 05:28:17 - 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"
+02/07/2026 05:28:17 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/datasets/rahul7star/hindi-speech-dataset/xet-read-token/0bfd5e2e4555ec80d7dd74b10442836d2e169be6 "HTTP/1.1 200 OK"
+
+
+data/train-00000-of-00036.parquet:   0%|          | 0.00/1.77G [00:00<?, ?B/s]
+
+data/train-00000-of-00036.parquet:   0%|          | 65.0k/1.77G [00:01<7:37:16, 64.3kB/s]
+
+data/train-00000-of-00036.parquet:   7%|▋         | 126M/1.77G [00:02<00:22, 73.9MB/s]   
+
+data/train-00000-of-00036.parquet:  25%|██▌       | 449M/1.77G [00:03<00:07, 187MB/s] 
+
+data/train-00000-of-00036.parquet:  43%|████▎     | 762M/1.77G [00:04<00:04, 235MB/s]
+
+data/train-00000-of-00036.parquet:  62%|██████▏   | 1.10G/1.77G [00:05<00:02, 272MB/s]
+
+data/train-00000-of-00036.parquet:  89%|████████▊ | 1.56G/1.77G [00:06<00:00, 331MB/s]
+data/train-00000-of-00036.parquet: 100%|██████████| 1.77G/1.77G [00:06<00:00, 275MB/s]
+
+Downloading data:   3%|▎         | 1/36 [00:06<03:46,  6.47s/files]02/07/2026 05:28:23 - 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"
+
+
+data/train-00001-of-00036.parquet:   0%|          | 0.00/496M [00:00<?, ?B/s]
+
+data/train-00001-of-00036.parquet:   1%|          | 4.05M/496M [00:01<02:01, 4.05MB/s]
+
+data/train-00001-of-00036.parquet:  49%|████▊     | 241M/496M [00:02<00:01, 141MB/s]  
+data/train-00001-of-00036.parquet: 100%|██████████| 496M/496M [00:02<00:00, 189MB/s]
+
+Downloading data:   6%|▌         | 2/36 [00:09<02:23,  4.23s/files]02/07/2026 05:28:26 - 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"
+
+
+data/train-00002-of-00036.parquet:   0%|          | 0.00/461M [00:00<?, ?B/s]
+
+data/train-00002-of-00036.parquet:   3%|▎         | 15.8M/461M [00:01<00:28, 15.7MB/s]
+
+data/train-00002-of-00036.parquet: 100%|██████████| 461M/461M [00:02<00:00, 202MB/s]  
+data/train-00002-of-00036.parquet: 100%|██████████| 461M/461M [00:02<00:00, 180MB/s]
+
+Downloading data:   8%|▊         | 3/36 [00:11<01:54,  3.48s/files]02/07/2026 05:28:29 - 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"
+
+
+data/train-00003-of-00036.parquet:   0%|          | 0.00/372M [00:00<?, ?B/s]
+
+data/train-00003-of-00036.parquet:   0%|          | 1.68M/372M [00:01<03:43, 1.66MB/s]
+
+data/train-00003-of-00036.parquet: 100%|██████████| 372M/372M [00:02<00:00, 178MB/s]  
+data/train-00003-of-00036.parquet: 100%|██████████| 372M/372M [00:02<00:00, 155MB/s]
+
+Downloading data:  11%|█         | 4/36 [00:14<01:38,  3.07s/files]02/07/2026 05:28:31 - 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"
+
+
+data/train-00004-of-00036.parquet:   0%|          | 0.00/373M [00:00<?, ?B/s]
+
+data/train-00004-of-00036.parquet:   2%|▏         | 8.18M/373M [00:01<00:44, 8.16MB/s]
+data/train-00004-of-00036.parquet: 100%|██████████| 373M/373M [00:01<00:00, 196MB/s]  
+
+Downloading data:  14%|█▍        | 5/36 [00:16<01:22,  2.67s/files]02/07/2026 05:28:33 - 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"
+
+
+data/train-00005-of-00036.parquet:   0%|          | 0.00/841M [00:00<?, ?B/s]
+
+data/train-00005-of-00036.parquet:   1%|          | 8.37M/841M [00:01<01:40, 8.30MB/s]
+
+data/train-00005-of-00036.parquet:  30%|██▉       | 249M/841M [00:02<00:04, 144MB/s]  
+
+data/train-00005-of-00036.parquet:  84%|████████▍ | 710M/841M [00:03<00:00, 288MB/s]
+data/train-00005-of-00036.parquet: 100%|██████████| 841M/841M [00:03<00:00, 219MB/s]
+
+Downloading data:  17%|█▋        | 6/36 [00:19<01:32,  3.08s/files]02/07/2026 05:28:37 - 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"
+
+
+data/train-00006-of-00036.parquet:   0%|          | 0.00/837M [00:00<?, ?B/s]
+
+data/train-00006-of-00036.parquet:   3%|▎         | 27.2M/837M [00:01<00:29, 27.2MB/s]
+
+data/train-00006-of-00036.parquet:  34%|███▍      | 283M/837M [00:02<00:03, 161MB/s]  
+
+data/train-00006-of-00036.parquet: 100%|██████████| 837M/837M [00:03<00:00, 250MB/s]
+data/train-00006-of-00036.parquet: 100%|██████████| 837M/837M [00:03<00:00, 221MB/s]
+
+Downloading data:  19%|█▉        | 7/36 [00:23<01:36,  3.34s/files]02/07/2026 05:28:41 - 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"
+
+
+data/train-00007-of-00036.parquet:   0%|          | 0.00/618M [00:00<?, ?B/s]
+
+data/train-00007-of-00036.parquet:   0%|          | 2.20M/618M [00:01<04:40, 2.20MB/s]
+
+data/train-00007-of-00036.parquet:  29%|██▉       | 178M/618M [00:02<00:04, 104MB/s]  
+
+data/train-00007-of-00036.parquet: 100%|██████████| 618M/618M [00:03<00:00, 224MB/s]
+data/train-00007-of-00036.parquet: 100%|██████████| 618M/618M [00:03<00:00, 186MB/s]
+
+Downloading data:  22%|██▏       | 8/36 [00:27<01:33,  3.34s/files]02/07/2026 05:28:44 - 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"
+
+
+data/train-00008-of-00036.parquet:   0%|          | 0.00/415M [00:00<?, ?B/s]
+
+data/train-00008-of-00036.parquet:   5%|▌         | 21.6M/415M [00:01<00:18, 21.2MB/s]
+data/train-00008-of-00036.parquet: 100%|██████████| 415M/415M [00:01<00:00, 214MB/s]  
+
+Downloading data:  25%|██▌       | 9/36 [00:29<01:18,  2.91s/files]02/07/2026 05:28:46 - 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"
+
+
+data/train-00009-of-00036.parquet:   0%|          | 0.00/303M [00:00<?, ?B/s]
+
+data/train-00009-of-00036.parquet:   5%|▍         | 14.1M/303M [00:01<00:20, 14.0MB/s]
+data/train-00009-of-00036.parquet: 100%|██████████| 303M/303M [00:01<00:00, 193MB/s]  
+
+Downloading data:  28%|██▊       | 10/36 [00:30<01:05,  2.50s/files]02/07/2026 05:28:48 - 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"
+
+
+data/train-00010-of-00036.parquet:   0%|          | 0.00/341M [00:00<?, ?B/s]
+
+data/train-00010-of-00036.parquet:  12%|█▏        | 40.2M/341M [00:01<00:07, 40.1MB/s]
+data/train-00010-of-00036.parquet: 100%|██████████| 341M/341M [00:01<00:00, 182MB/s]  
+
+Downloading data:  31%|███       | 11/36 [00:32<00:58,  2.34s/files]02/07/2026 05:28:50 - 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"
+
+
+data/train-00011-of-00036.parquet:   0%|          | 0.00/440M [00:00<?, ?B/s]
+
+data/train-00011-of-00036.parquet:   2%|▏         | 10.8M/440M [00:01<00:39, 10.8MB/s]
+
+data/train-00011-of-00036.parquet: 100%|██████████| 440M/440M [00:02<00:00, 244MB/s]  
+data/train-00011-of-00036.parquet: 100%|██████████| 440M/440M [00:02<00:00, 211MB/s]
+
+Downloading data:  33%|███▎      | 12/36 [00:34<00:54,  2.27s/files]02/07/2026 05:28:52 - 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"
+
+
+data/train-00012-of-00036.parquet:   0%|          | 0.00/412M [00:00<?, ?B/s]
+
+data/train-00012-of-00036.parquet:   9%|▊         | 35.9M/412M [00:01<00:10, 35.9MB/s]
+data/train-00012-of-00036.parquet: 100%|██████████| 412M/412M [00:01<00:00, 240MB/s]  
+
+Downloading data:  36%|███▌      | 13/36 [00:36<00:48,  2.11s/files]02/07/2026 05:28:53 - 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"
+
+
+data/train-00013-of-00036.parquet:   0%|          | 0.00/397M [00:00<?, ?B/s]
+
+data/train-00013-of-00036.parquet:   6%|▌         | 24.1M/397M [00:01<00:15, 24.0MB/s]
+data/train-00013-of-00036.parquet: 100%|██████████| 397M/397M [00:01<00:00, 221MB/s]  
+
+Downloading data:  39%|███▉      | 14/36 [00:38<00:44,  2.02s/files]02/07/2026 05:28:55 - 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"
+
+
+data/train-00014-of-00036.parquet:   0%|          | 0.00/397M [00:00<?, ?B/s]
+
+data/train-00014-of-00036.parquet:   2%|▏         | 8.19M/397M [00:01<00:47, 8.12MB/s]
+
+data/train-00014-of-00036.parquet:  35%|███▌      | 139M/397M [00:02<00:03, 80.0MB/s] 
+data/train-00014-of-00036.parquet: 100%|██████████| 397M/397M [00:02<00:00, 136MB/s] 
+
+Downloading data:  42%|████▏     | 15/36 [00:41<00:48,  2.31s/files]02/07/2026 05:28:58 - 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"
+
+
+data/train-00015-of-00036.parquet:   0%|          | 0.00/389M [00:00<?, ?B/s]
+
+data/train-00015-of-00036.parquet:   1%|          | 2.39M/389M [00:01<02:42, 2.38MB/s]
+
+data/train-00015-of-00036.parquet:  83%|████████▎ | 322M/389M [00:02<00:00, 186MB/s]  
+data/train-00015-of-00036.parquet: 100%|██████████| 389M/389M [00:02<00:00, 181MB/s]
+
+Downloading data:  44%|████▍     | 16/36 [00:43<00:45,  2.27s/files]02/07/2026 05:29:00 - 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"
+
+
+data/train-00016-of-00036.parquet:   0%|          | 0.00/384M [00:00<?, ?B/s]
+
+data/train-00016-of-00036.parquet:   0%|          | 14.6k/384M [00:01<9:36:49, 11.1kB/s]
+
+data/train-00016-of-00036.parquet: 100%|██████████| 384M/384M [00:02<00:00, 178MB/s]    
+data/train-00016-of-00036.parquet: 100%|██████████| 384M/384M [00:02<00:00, 151MB/s]
+
+Downloading data:  47%|████▋     | 17/36 [00:46<00:44,  2.36s/files]02/07/2026 05:29:03 - 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"
+
+
+data/train-00017-of-00036.parquet:   0%|          | 0.00/441M [00:00<?, ?B/s]
+
+data/train-00017-of-00036.parquet:   0%|          | 8.34k/441M [00:01<14:43:47, 8.32kB/s]
+
+data/train-00017-of-00036.parquet:  69%|██████▉   | 304M/441M [00:02<00:00, 178MB/s]     
+data/train-00017-of-00036.parquet: 100%|██████████| 441M/441M [00:02<00:00, 161MB/s]
+
+Downloading data:  50%|█████     | 18/36 [00:48<00:44,  2.48s/files]02/07/2026 05:29:06 - 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"
+
+
+data/train-00018-of-00036.parquet:   0%|          | 0.00/571M [00:00<?, ?B/s]
+
+data/train-00018-of-00036.parquet:   4%|▍         | 25.1M/571M [00:01<00:21, 25.0MB/s]
+
+data/train-00018-of-00036.parquet:  67%|██████▋   | 382M/571M [00:02<00:00, 220MB/s]  
+data/train-00018-of-00036.parquet: 100%|██████████| 571M/571M [00:03<00:00, 168MB/s]
+
+Downloading data:  53%|█████▎    | 19/36 [00:52<00:47,  2.77s/files]02/07/2026 05:29:09 - 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"
+
+
+data/train-00019-of-00036.parquet:   0%|          | 0.00/413M [00:00<?, ?B/s]
+
+data/train-00019-of-00036.parquet:  10%|▉         | 40.5M/413M [00:01<00:09, 40.5MB/s]
+data/train-00019-of-00036.parquet: 100%|██████████| 413M/413M [00:01<00:00, 207MB/s]  
+
+Downloading data:  56%|█████▌    | 20/36 [00:54<00:40,  2.55s/files]02/07/2026 05:29:11 - 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"
+
+
+data/train-00020-of-00036.parquet:   0%|          | 0.00/417M [00:00<?, ?B/s]
+
+data/train-00020-of-00036.parquet:   7%|▋         | 29.3M/417M [00:01<00:13, 29.2MB/s]
+
+data/train-00020-of-00036.parquet: 100%|██████████| 417M/417M [00:02<00:00, 221MB/s]  
+data/train-00020-of-00036.parquet: 100%|██████████| 417M/417M [00:02<00:00, 194MB/s]
+
+Downloading data:  58%|█████▊    | 21/36 [00:56<00:36,  2.43s/files]02/07/2026 05:29:13 - 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"
+
+
+data/train-00021-of-00036.parquet:   0%|          | 0.00/401M [00:00<?, ?B/s]
+
+data/train-00021-of-00036.parquet:   5%|▍         | 18.6M/401M [00:01<00:20, 18.5MB/s]
+
+data/train-00021-of-00036.parquet: 100%|██████████| 401M/401M [00:02<00:00, 210MB/s]  
+data/train-00021-of-00036.parquet: 100%|██████████| 401M/401M [00:02<00:00, 184MB/s]
+
+Downloading data:  61%|██████    | 22/36 [00:58<00:33,  2.36s/files]02/07/2026 05:29:16 - 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"
+
+
+data/train-00022-of-00036.parquet:   0%|          | 0.00/373M [00:00<?, ?B/s]
+
+data/train-00022-of-00036.parquet:   4%|▍         | 16.3M/373M [00:01<00:22, 16.2MB/s]
+data/train-00022-of-00036.parquet: 100%|██████████| 373M/373M [00:01<00:00, 194MB/s]  
+
+Downloading data:  64%|██████▍   | 23/36 [01:00<00:29,  2.24s/files]02/07/2026 05:29:18 - 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"
+
+
+data/train-00023-of-00036.parquet:   0%|          | 0.00/374M [00:00<?, ?B/s]
+
+data/train-00023-of-00036.parquet:   4%|▍         | 14.6M/374M [00:01<00:24, 14.5MB/s]
+
+data/train-00023-of-00036.parquet: 100%|██████████| 374M/374M [00:02<00:00, 186MB/s]  
+data/train-00023-of-00036.parquet: 100%|██████████| 374M/374M [00:02<00:00, 164MB/s]
+
+Downloading data:  67%|██████▋   | 24/36 [01:02<00:27,  2.26s/files]02/07/2026 05:29:20 - 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"
+
+
+data/train-00024-of-00036.parquet:   0%|          | 0.00/531M [00:00<?, ?B/s]
+
+data/train-00024-of-00036.parquet:   2%|▏         | 9.64M/531M [00:01<00:54, 9.54MB/s]
+
+data/train-00024-of-00036.parquet:  61%|██████▏   | 326M/531M [00:02<00:01, 189MB/s]  
+data/train-00024-of-00036.parquet: 100%|██████████| 531M/531M [00:02<00:00, 192MB/s]
+
+Downloading data:  69%|██████▉   | 25/36 [01:05<00:26,  2.43s/files]02/07/2026 05:29:23 - 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"
+
+
+data/train-00025-of-00036.parquet:   0%|          | 0.00/542M [00:00<?, ?B/s]
+
+data/train-00025-of-00036.parquet:   2%|▏         | 10.4M/542M [00:01<00:51, 10.4MB/s]
+
+data/train-00025-of-00036.parquet:  55%|█████▌    | 299M/542M [00:02<00:01, 174MB/s]  
+
+data/train-00025-of-00036.parquet: 100%|██████████| 542M/542M [00:03<00:00, 196MB/s]
+data/train-00025-of-00036.parquet: 100%|██████████| 542M/542M [00:03<00:00, 175MB/s]
+
+Downloading data:  72%|███████▏  | 26/36 [01:08<00:26,  2.64s/files]02/07/2026 05:29:26 - 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"
+
+
+data/train-00026-of-00036.parquet:   0%|          | 0.00/434M [00:00<?, ?B/s]
+
+data/train-00026-of-00036.parquet:   3%|▎         | 13.9M/434M [00:01<00:30, 13.9MB/s]
+
+data/train-00026-of-00036.parquet: 100%|██████████| 434M/434M [00:02<00:00, 236MB/s]  
+data/train-00026-of-00036.parquet: 100%|██████████| 434M/434M [00:02<00:00, 204MB/s]
+
+Downloading data:  75%|███████▌  | 27/36 [01:11<00:22,  2.49s/files]02/07/2026 05:29:28 - 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"
+
+
+data/train-00027-of-00036.parquet:   0%|          | 0.00/366M [00:00<?, ?B/s]
+
+data/train-00027-of-00036.parquet:   7%|▋         | 24.2M/366M [00:01<00:14, 24.1MB/s]
+data/train-00027-of-00036.parquet: 100%|██████████| 366M/366M [00:01<00:00, 193MB/s]  
+
+Downloading data:  78%|███████▊  | 28/36 [01:12<00:18,  2.32s/files]02/07/2026 05:29:30 - 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"
+
+
+data/train-00028-of-00036.parquet:   0%|          | 0.00/374M [00:00<?, ?B/s]
+
+data/train-00028-of-00036.parquet:   0%|          | 73.2k/374M [00:01<1:31:08, 68.4kB/s]
+data/train-00028-of-00036.parquet: 100%|██████████| 374M/374M [00:02<00:00, 183MB/s]    
+
+Downloading data:  81%|████████  | 29/36 [01:15<00:15,  2.25s/files]02/07/2026 05:29:32 - 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"
+
+
+data/train-00029-of-00036.parquet:   0%|          | 0.00/402M [00:00<?, ?B/s]
+
+data/train-00029-of-00036.parquet:   7%|▋         | 26.9M/402M [00:01<00:13, 26.9MB/s]
+data/train-00029-of-00036.parquet: 100%|██████████| 402M/402M [00:01<00:00, 223MB/s]  
+
+Downloading data:  83%|████████▎ | 30/36 [01:16<00:12,  2.12s/files]02/07/2026 05:29:34 - 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"
+
+
+data/train-00030-of-00036.parquet:   0%|          | 0.00/400M [00:00<?, ?B/s]
+
+data/train-00030-of-00036.parquet:   3%|▎         | 10.9M/400M [00:01<00:35, 10.9MB/s]
+
+data/train-00030-of-00036.parquet: 100%|██████████| 400M/400M [00:02<00:00, 171MB/s]  
+data/train-00030-of-00036.parquet: 100%|██████████| 400M/400M [00:02<00:00, 153MB/s]
+
+Downloading data:  86%|████████▌ | 31/36 [01:19<00:11,  2.28s/files]02/07/2026 05:29:36 - 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"
+
+
+data/train-00031-of-00036.parquet:   0%|          | 0.00/382M [00:00<?, ?B/s]
+
+data/train-00031-of-00036.parquet:   0%|          | 359k/382M [00:01<17:52, 356kB/s]
+
+data/train-00031-of-00036.parquet:  87%|████████▋ | 334M/382M [00:02<00:00, 196MB/s]
+data/train-00031-of-00036.parquet: 100%|██████████| 382M/382M [00:02<00:00, 170MB/s]
+
+Downloading data:  89%|████████▉ | 32/36 [01:21<00:09,  2.28s/files]02/07/2026 05:29:39 - 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"
+
+
+data/train-00032-of-00036.parquet:   0%|          | 0.00/380M [00:00<?, ?B/s]
+
+data/train-00032-of-00036.parquet:   0%|          | 94.5k/380M [00:01<1:07:00, 94.4kB/s]
+
+data/train-00032-of-00036.parquet: 100%|██████████| 380M/380M [00:02<00:00, 170MB/s]    
+data/train-00032-of-00036.parquet: 100%|██████████| 380M/380M [00:02<00:00, 150MB/s]
+
+Downloading data:  92%|█████████▏| 33/36 [01:24<00:07,  2.37s/files]02/07/2026 05:29:41 - 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"
+
+
+data/train-00033-of-00036.parquet:   0%|          | 0.00/376M [00:00<?, ?B/s]
+
+data/train-00033-of-00036.parquet:   1%|▏         | 4.83M/376M [00:01<01:17, 4.81MB/s]
+data/train-00033-of-00036.parquet: 100%|██████████| 376M/376M [00:01<00:00, 188MB/s]  
+
+Downloading data:  94%|█████████▍| 34/36 [01:26<00:04,  2.27s/files]02/07/2026 05:29:43 - 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"
+
+
+data/train-00034-of-00036.parquet:   0%|          | 0.00/372M [00:00<?, ?B/s]
+
+data/train-00034-of-00036.parquet:   2%|▏         | 6.35M/372M [00:01<00:57, 6.33MB/s]
+data/train-00034-of-00036.parquet: 100%|██████████| 372M/372M [00:01<00:00, 192MB/s]  
+
+Downloading data:  97%|█████████▋| 35/36 [01:28<00:02,  2.18s/files]02/07/2026 05:29:45 - 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"
+
+
+data/train-00035-of-00036.parquet:   0%|          | 0.00/373M [00:00<?, ?B/s]
+
+data/train-00035-of-00036.parquet:   3%|▎         | 9.34M/373M [00:01<00:39, 9.30MB/s]
+
+data/train-00035-of-00036.parquet: 100%|██████████| 373M/373M [00:02<00:00, 210MB/s]  
+data/train-00035-of-00036.parquet: 100%|██████████| 373M/373M [00:02<00:00, 181MB/s]
+
+Downloading data: 100%|██████████| 36/36 [01:30<00:00,  2.15s/files]
+Downloading data: 100%|██████████| 36/36 [01:30<00:00,  2.51s/files]
+02/07/2026 05:29:47 - 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"
+
+
+data/validation-00000-of-00001.parquet:   0%|          | 0.00/162M [00:00<?, ?B/s]
+
+data/validation-00000-of-00001.parquet:  37%|███▋      | 59.6M/162M [00:01<00:01, 58.8MB/s]
+data/validation-00000-of-00001.parquet: 100%|██████████| 162M/162M [00:01<00:00, 131MB/s]  
+02/07/2026 05:29:49 - 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"
+
+
+data/test-00000-of-00001.parquet:   0%|          | 0.00/306M [00:00<?, ?B/s]
+
+data/test-00000-of-00001.parquet:   3%|▎         | 9.32M/306M [00:01<00:31, 9.29MB/s]
+
+data/test-00000-of-00001.parquet: 100%|██████████| 306M/306M [00:02<00:00, 158MB/s]  
+data/test-00000-of-00001.parquet: 100%|██████████| 306M/306M [00:02<00:00, 138MB/s]
+
+
+Generating train split:   0%|          | 0/145152 [00:00<?, ? examples/s]
+
+Generating train split:   0%|          | 200/145152 [00:01<17:39, 136.87 examples/s]
+
+Generating train split:   0%|          | 500/145152 [00:02<12:29, 193.04 examples/s]
+
+Generating train split:   1%|          | 800/145152 [00:03<11:21, 211.79 examples/s]
+
+Generating train split:   1%|          | 1100/145152 [00:05<10:46, 222.75 examples/s]
+
+Generating train split:   1%|          | 1400/145152 [00:06<10:17, 232.66 examples/s]
+
+Generating train split:   1%|          | 1700/145152 [00:07<10:12, 234.05 examples/s]
+
+Generating train split:   1%|▏         | 2000/145152 [00:09<10:15, 232.74 examples/s]
+
+Generating train split:   3%|▎         | 3800/145152 [00:10<03:36, 651.42 examples/s]
+
+Generating train split:   4%|▍         | 5632/145152 [00:11<02:24, 963.12 examples/s]
+
+Generating train split:   5%|▌         | 7832/145152 [00:12<01:48, 1271.33 examples/s]
+
+Generating train split:   7%|▋         | 9864/145152 [00:13<01:31, 1473.19 examples/s]
+
+Generating train split:   8%|▊         | 12196/145152 [00:14<01:18, 1694.99 examples/s]
+
+Generating train split:  10%|█         | 14796/145152 [00:15<01:07, 1922.04 examples/s]
+
+Generating train split:  12%|█▏        | 17628/145152 [00:16<00:58, 2168.74 examples/s]
+
+Generating train split:  14%|█▍        | 20360/145152 [00:17<00:54, 2298.53 examples/s]
+
+Generating train split:  16%|█▌        | 22760/145152 [00:19<01:10, 1742.80 examples/s]
+
+Generating train split:  17%|█▋        | 24792/145152 [00:21<01:19, 1518.67 examples/s]
+
+Generating train split:  18%|█▊        | 26592/145152 [00:22<01:24, 1401.27 examples/s]
+
+Generating train split:  20%|█▉        | 28324/145152 [00:24<01:29, 1311.22 examples/s]
+
+Generating train split:  21%|██        | 29824/145152 [00:25<01:25, 1345.45 examples/s]
+
+Generating train split:  22%|██▏       | 31624/145152 [00:26<01:18, 1447.83 examples/s]
+
+Generating train split:  23%|██▎       | 33456/145152 [00:27<01:12, 1537.19 examples/s]
+
+Generating train split:  25%|██▌       | 36688/145152 [00:28<00:55, 1938.33 examples/s]
+
+Generating train split:  28%|██▊       | 40420/145152 [00:29<00:43, 2382.77 examples/s]
+
+Generating train split:  30%|███       | 43720/145152 [00:30<00:39, 2554.01 examples/s]
+
+Generating train split:  32%|███▏      | 46452/145152 [00:31<00:39, 2484.61 examples/s]
+
+Generating train split:  34%|███▎      | 48984/145152 [00:33<00:39, 2413.22 examples/s]
+
+Generating train split:  36%|███▌      | 51684/145152 [00:34<00:38, 2440.25 examples/s]
+
+Generating train split:  38%|███▊      | 54516/145152 [00:35<00:36, 2470.40 examples/s]
+
+Generating train split:  39%|███▉      | 57048/145152 [00:36<00:35, 2465.42 examples/s]
+
+Generating train split:  41%|████      | 59748/145152 [00:37<00:34, 2500.85 examples/s]
+
+Generating train split:  43%|████▎     | 62580/145152 [00:38<00:32, 2561.25 examples/s]
+
+Generating train split:  45%|████▌     | 65412/145152 [00:39<00:30, 2585.41 examples/s]
+
+Generating train split:  47%|████▋     | 68112/145152 [00:40<00:29, 2582.27 examples/s]
+
+Generating train split:  49%|████▉     | 70944/145152 [00:41<00:28, 2611.47 examples/s]
+
+Generating train split:  51%|█████     | 73576/145152 [00:43<00:30, 2339.59 examples/s]
+
+Generating train split:  52%|█████▏    | 75976/145152 [00:44<00:32, 2152.89 examples/s]
+
+Generating train split:  54%|█████▍    | 78408/145152 [00:45<00:30, 2176.73 examples/s]
+
+Generating train split:  56%|█████▌    | 80940/145152 [00:46<00:28, 2241.15 examples/s]
+
+Generating train split:  58%|█████▊    | 83640/145152 [00:47<00:26, 2319.10 examples/s]
+
+Generating train split:  59%|█████▉    | 86172/145152 [00:48<00:24, 2363.50 examples/s]
+
+Generating train split:  61%|██████▏   | 89004/145152 [00:49<00:23, 2434.11 examples/s]
+
+Generating train split:  63%|██████▎   | 92004/145152 [00:50<00:21, 2530.53 examples/s]
+
+Generating train split:  65%|██████▌   | 94836/145152 [00:51<00:19, 2576.81 examples/s]
+
+Generating train split:  67%|██████▋   | 97468/145152 [00:52<00:18, 2561.68 examples/s]
+
+Generating train split:  69%|██████▉   | 100068/145152 [00:54<00:19, 2354.85 examples/s]
+
+Generating train split:  71%|███████   | 102600/145152 [00:55<00:19, 2192.23 examples/s]
+
+Generating train split:  72%|███████▏  | 104932/145152 [00:56<00:18, 2118.58 examples/s]
+
+Generating train split:  74%|███████▍  | 107132/145152 [00:57<00:17, 2122.32 examples/s]
+
+Generating train split:  76%|███████▌  | 110064/145152 [00:58<00:15, 2331.15 examples/s]
+
+Generating train split:  78%|███████▊  | 112996/145152 [00:59<00:13, 2444.29 examples/s]
+
+Generating train split:  80%|███████▉  | 115896/145152 [01:00<00:11, 2510.08 examples/s]
+
+Generating train split:  82%|████████▏ | 118428/145152 [01:02<00:10, 2479.28 examples/s]
+
+Generating train split:  83%|████████▎ | 121060/145152 [01:03<00:09, 2511.85 examples/s]
+
+Generating train split:  85%|████████▌ | 123660/145152 [01:04<00:08, 2514.99 examples/s]
+
+Generating train split:  87%|████████▋ | 126192/145152 [01:05<00:07, 2496.21 examples/s]
+
+Generating train split:  89%|███��████▉ | 128892/145152 [01:06<00:06, 2542.71 examples/s]
+
+Generating train split:  91%|█████████ | 131724/145152 [01:07<00:05, 2560.40 examples/s]
+
+Generating train split:  93%|█████████▎| 134556/145152 [01:08<00:04, 2632.84 examples/s]
+
+Generating train split:  95%|█████████▍| 137388/145152 [01:09<00:02, 2644.04 examples/s]
+
+Generating train split:  97%|█████████▋| 140088/145152 [01:10<00:01, 2656.71 examples/s]
+
+Generating train split:  98%|█████████▊| 142920/145152 [01:11<00:00, 2685.45 examples/s]
+Generating train split: 100%|██████████| 145152/145152 [01:12<00:00, 2013.67 examples/s]
+
+
+Generating validation split:   0%|          | 0/239 [00:00<?, ? examples/s]
+Generating validation split: 100%|██████████| 239/239 [00:00<00:00, 253.06 examples/s]
+
+
+Generating test split:   0%|          | 0/418 [00:00<?, ? examples/s]
+
+Generating test split:  48%|████▊     | 200/418 [00:01<00:01, 160.93 examples/s]
+Generating test split: 100%|██████████| 418/418 [00:01<00:00, 242.41 examples/s]
+02/07/2026 05:31:06 - INFO - __main__ - *** Training T3 model ***
+
+
+  0%|          | 0/145152 [00:00<?, ?it/s]Traceback (most recent call last):
   File "/app/chatterbox-multilingual-finetuning/src/finetune_t3.py", line 849, in <module>
     main()
     ~~~~^^
-  File "/app/chatterbox-multilingual-finetuning/src/finetune_t3.py", line 616, in main
-    chatterbox_model = ChatterboxMultilingualTTS.from_pretrained(device="cpu")
-  File "/app/chatterbox-multilingual-finetuning/src/chatterbox/mtl_tts.py", line 201, in from_pretrained
-    return cls.from_local(ckpt_dir, device)
-           ~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^
-  File "/app/chatterbox-multilingual-finetuning/src/chatterbox/mtl_tts.py", line 180, in from_local
-    conds = Conditionals.load(builtin_voice).to(device)
-  File "/app/chatterbox-multilingual-finetuning/src/chatterbox/mtl_tts.py", line 106, in to
-    self.t3 = self.t3.to(device)
-              ~~~~~~~~~~^^^^^^^^
-TypeError: T3Cond.to() takes 1 positional argument but 2 were given
+  File "/app/chatterbox-multilingual-finetuning/src/finetune_t3.py", line 796, in main
+    train_result = trainer_instance.train(
+        resume_from_checkpoint=training_args.resume_from_checkpoint
+    )
+  File "/usr/local/lib/python3.13/site-packages/transformers/trainer.py", line 2170, in train
+    return inner_training_loop(
+        args=args,
+    ...<2 lines>...
+        ignore_keys_for_eval=ignore_keys_for_eval,
+    )
+  File "/usr/local/lib/python3.13/site-packages/transformers/trainer.py", line 2442, in _inner_training_loop
+    self._evaluate(trial, ignore_keys_for_eval, skip_scheduler=True)
+    ~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/usr/local/lib/python3.13/site-packages/transformers/trainer.py", line 2970, in _evaluate
+    metrics = self.evaluate(ignore_keys=ignore_keys_for_eval)
+  File "/usr/local/lib/python3.13/site-packages/transformers/trainer.py", line 4290, in evaluate
+    output = self.evaluation_loop(
+        eval_dataloader,
+    ...<5 lines>...
+        metric_key_prefix=metric_key_prefix,
+    )
+  File "/usr/local/lib/python3.13/site-packages/transformers/trainer.py", line 4468, in evaluation_loop
+    for step, inputs in enumerate(dataloader):
+                        ~~~~~~~~~^^^^^^^^^^^^
+  File "/usr/local/lib/python3.13/site-packages/accelerate/data_loader.py", line 567, in __iter__
+    current_batch = next(dataloader_iter)
+  File "/usr/local/lib/python3.13/site-packages/torch/utils/data/dataloader.py", line 741, in __next__
+    data = self._next_data()
+  File "/usr/local/lib/python3.13/site-packages/torch/utils/data/dataloader.py", line 1548, in _next_data
+    return self._process_data(data, worker_id)
+           ~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^
+  File "/usr/local/lib/python3.13/site-packages/torch/utils/data/dataloader.py", line 1586, in _process_data
+    data.reraise()
+    ~~~~~~~~~~~~^^
+  File "/usr/local/lib/python3.13/site-packages/torch/_utils.py", line 775, in reraise
+    raise exception
+ImportError: Caught ImportError in DataLoader worker process 0.
+Original Traceback (most recent call last):
+  File "/usr/local/lib/python3.13/site-packages/torch/utils/data/_utils/worker.py", line 358, in _worker_loop
+    data = fetcher.fetch(index)  # type: ignore[possibly-undefined]
+  File "/usr/local/lib/python3.13/site-packages/torch/utils/data/_utils/fetch.py", line 54, in fetch
+    data = [self.dataset[idx] for idx in possibly_batched_index]
+            ~~~~~~~~~~~~^^^^^
+  File "/app/chatterbox-multilingual-finetuning/src/finetune_t3.py", line 239, in __getitem__
+    wav_16k, text = self._load_audio_text_from_item(idx)
+                    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^
+  File "/app/chatterbox-multilingual-finetuning/src/finetune_t3.py", line 187, in _load_audio_text_from_item
+    item = self.dataset_source[idx]
+           ~~~~~~~~~~~~~~~~~~~^^^^^
+  File "/usr/local/lib/python3.13/site-packages/datasets/arrow_dataset.py", line 2878, in __getitem__
+    return self._getitem(key)
+           ~~~~~~~~~~~~~^^^^^
+  File "/usr/local/lib/python3.13/site-packages/datasets/arrow_dataset.py", line 2860, in _getitem
+    formatted_output = format_table(
+        pa_subtable, key, formatter=formatter, format_columns=format_columns, output_all_columns=output_all_columns
+    )
+  File "/usr/local/lib/python3.13/site-packages/datasets/formatting/formatting.py", line 658, in format_table
+    return formatter(pa_table, query_type=query_type)
+  File "/usr/local/lib/python3.13/site-packages/datasets/formatting/formatting.py", line 411, in __call__
+    return self.format_row(pa_table)
+           ~~~~~~~~~~~~~~~^^^^^^^^^^
+  File "/usr/local/lib/python3.13/site-packages/datasets/formatting/formatting.py", line 460, in format_row
+    row = self.python_features_decoder.decode_row(row)
+  File "/usr/local/lib/python3.13/site-packages/datasets/formatting/formatting.py", line 224, in decode_row
+    return self.features.decode_example(row, token_per_repo_id=self.token_per_repo_id) if self.features else row
+           ~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/usr/local/lib/python3.13/site-packages/datasets/features/features.py", line 2111, in decode_example
+    column_name: decode_nested_example(feature, value, token_per_repo_id=token_per_repo_id)
+                 ~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/usr/local/lib/python3.13/site-packages/datasets/features/features.py", line 1419, in decode_nested_example
+    return schema.decode_example(obj, token_per_repo_id=token_per_repo_id) if obj is not None else None
+           ~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/usr/local/lib/python3.13/site-packages/datasets/features/audio.py", line 186, in decode_example
+    raise ImportError("To support decoding audio data, please install 'torchcodec'.")
+ImportError: To support decoding audio data, please install 'torchcodec'.
+
+
+  0%|          | 0/145152 [00:02<?, ?it/s]