Chatterbox fine-tuned model + logs

Browse files

Files changed (2) hide show

runs/Feb07_06-40-02_r-rahul7star-chatterbox-train-g7zglrbi-16d21-bvzlr/events.out.tfevents.1770442802.r-rahul7star-chatterbox-train-g7zglrbi-16d21-bvzlr.98.0 +3 -0
training.log +608 -203

runs/Feb07_06-40-02_r-rahul7star-chatterbox-train-g7zglrbi-16d21-bvzlr/events.out.tfevents.1770442802.r-rahul7star-chatterbox-train-g7zglrbi-16d21-bvzlr.98.0 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:87faa16126560a7c98e2d601528cffca4a0dead499df30fe76947d42f2ad6baf
+size 4097

training.log CHANGED Viewed

@@ -4,458 +4,863 @@ Resolved paths:
 - output_dir: /app/checkpoints/v1
 Starting training...
 /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
 README.md:   0%|          | 0.00/591 [00:00<?, ?B/s][A
-README.md: 100%|██████████| 591/591 [00:00<00:00, 2.77MB/s]
-Downloading data:   0%|          | 0/36 [00:00<?, ?files/s]
 data/train-00000-of-00036.parquet:   0%|          | 0.00/1.77G [00:00<?, ?B/s][A
-data/train-00000-of-00036.parquet:   0%|          | 11.1k/1.77G [00:01<45:08:35, 10.9kB/s][A
-data/train-00000-of-00036.parquet:  10%|█         | 185M/1.77G [00:02<00:14, 108MB/s]     [A
-data/train-00000-of-00036.parquet:  29%|██▉       | 512M/1.77G [00:03<00:06, 207MB/s][A
-data/train-00000-of-00036.parquet:  49%|████▊     | 858M/1.77G [00:04<00:03, 261MB/s][A
-data/train-00000-of-00036.parquet:  76%|███████▋  | 1.35G/1.77G [00:05<00:01, 343MB/s][A
-data/train-00000-of-00036.parquet: 100%|██████████| 1.77G/1.77G [00:05<00:00, 305MB/s]
-Downloading data:   3%|▎         | 1/36 [00:05<03:24,  5.84s/files]
 data/train-00001-of-00036.parquet:   0%|          | 0.00/496M [00:00<?, ?B/s][A
-data/train-00001-of-00036.parquet:   4%|▍         | 19.6M/496M [00:01<00:24, 19.6MB/s][A
-data/train-00001-of-00036.parquet: 100%|██████████| 496M/496M [00:02<00:00, 265MB/s]  [A
-data/train-00001-of-00036.parquet: 100%|██████████| 496M/496M [00:02<00:00, 230MB/s]
-Downloading data:   6%|▌         | 2/36 [00:08<02:05,  3.70s/files]
 data/train-00002-of-00036.parquet:   0%|          | 0.00/461M [00:00<?, ?B/s][A
-data/train-00002-of-00036.parquet:   8%|▊         | 37.0M/461M [00:01<00:11, 36.9MB/s][A
-data/train-00002-of-00036.parquet: 100%|██████████| 461M/461M [00:01<00:00, 238MB/s]
-Downloading data:   8%|▊         | 3/36 [00:09<01:35,  2.90s/files]
 data/train-00003-of-00036.parquet:   0%|          | 0.00/372M [00:00<?, ?B/s][A
-data/train-00003-of-00036.parquet:  12%|█▏        | 44.2M/372M [00:01<00:07, 43.8MB/s][A
-data/train-00003-of-00036.parquet: 100%|██████████| 372M/372M [00:01<00:00, 215MB/s]
-Downloading data:  11%|█         | 4/36 [00:11<01:18,  2.45s/files]
 data/train-00004-of-00036.parquet:   0%|          | 0.00/373M [00:00<?, ?B/s][A
-data/train-00004-of-00036.parquet:  10%|█         | 37.5M/373M [00:01<00:08, 37.5MB/s][A
-data/train-00004-of-00036.parquet: 100%|██████████| 373M/373M [00:01<00:00, 236MB/s]
-Downloading data:  14%|█▍        | 5/36 [00:13<01:06,  2.14s/files]
 data/train-00005-of-00036.parquet:   0%|          | 0.00/841M [00:00<?, ?B/s][A
-data/train-00005-of-00036.parquet:   6%|▌         | 50.5M/841M [00:01<00:15, 50.4MB/s][A
-data/train-00005-of-00036.parquet:  38%|███▊      | 319M/841M [00:02<00:02, 179MB/s]  [A
-data/train-00005-of-00036.parquet: 100%|██████████| 841M/841M [00:03<00:00, 289MB/s][A
-data/train-00005-of-00036.parquet: 100%|██████████| 841M/841M [00:03<00:00, 251MB/s]
-Downloading data:  17%|█▋        | 6/36 [00:16<01:16,  2.56s/files]
 data/train-00006-of-00036.parquet:   0%|          | 0.00/837M [00:00<?, ?B/s][A
-data/train-00006-of-00036.parquet:   4%|▎         | 30.6M/837M [00:01<00:26, 30.5MB/s][A
-data/train-00006-of-00036.parquet:  34%|███▍      | 287M/837M [00:02<00:03, 163MB/s]  [A
-data/train-00006-of-00036.parquet: 100%|██████████| 837M/837M [00:03<00:00, 290MB/s][A
-data/train-00006-of-00036.parquet: 100%|██████████| 837M/837M [00:03<00:00, 248MB/s]
-Downloading data:  19%|█▉        | 7/36 [00:20<01:22,  2.84s/files]
 data/train-00007-of-00036.parquet:   0%|          | 0.00/618M [00:00<?, ?B/s][A
-data/train-00007-of-00036.parquet:   4%|▎         | 22.1M/618M [00:01<00:27, 22.1MB/s][A
-data/train-00007-of-00036.parquet:  53%|█████▎    | 327M/618M [00:02<00:01, 188MB/s]  [A
-data/train-00007-of-00036.parquet: 100%|██████████| 618M/618M [00:03<00:00, 212MB/s][A
-data/train-00007-of-00036.parquet: 100%|██████████| 618M/618M [00:03<00:00, 191MB/s]
-Downloading data:  22%|██▏       | 8/36 [00:23<01:23,  2.98s/files]
 data/train-00008-of-00036.parquet:   0%|          | 0.00/415M [00:00<?, ?B/s][A
-data/train-00008-of-00036.parquet:   9%|▊         | 35.9M/415M [00:01<00:10, 35.8MB/s][A
-data/train-00008-of-00036.parquet: 100%|██████████| 415M/415M [00:01<00:00, 254MB/s]
-Downloading data:  25%|██▌       | 9/36 [00:25<01:09,  2.57s/files]
 data/train-00009-of-00036.parquet:   0%|          | 0.00/303M [00:00<?, ?B/s][A
-data/train-00009-of-00036.parquet:  25%|██▌       | 77.0M/303M [00:01<00:02, 77.0MB/s][A
-data/train-00009-of-00036.parquet: 100%|██████████| 303M/303M [00:01<00:00, 219MB/s]
-Downloading data:  28%|██▊       | 10/36 [00:26<00:57,  2.21s/files]
 data/train-00010-of-00036.parquet:   0%|          | 0.00/341M [00:00<?, ?B/s][A
-data/train-00010-of-00036.parquet:  20%|██        | 68.7M/341M [00:01<00:04, 67.4MB/s][A
-data/train-00010-of-00036.parquet: 100%|██████████| 341M/341M [00:01<00:00, 176MB/s]
-Downloading data:  31%|███       | 11/36 [00:28<00:53,  2.13s/files]
 data/train-00011-of-00036.parquet:   0%|          | 0.00/440M [00:00<?, ?B/s][A
-data/train-00011-of-00036.parquet:   6%|▌         | 24.6M/440M [00:01<00:16, 24.5MB/s][A
-data/train-00011-of-00036.parquet: 100%|██████████| 440M/440M [00:01<00:00, 233MB/s]
-Downloading data:  33%|███▎      | 12/36 [00:30<00:49,  2.08s/files]
 data/train-00012-of-00036.parquet:   0%|          | 0.00/412M [00:00<?, ?B/s][A
-data/train-00012-of-00036.parquet:  11%|█▏        | 46.4M/412M [00:01<00:07, 46.0MB/s][A
-data/train-00012-of-00036.parquet: 100%|██████████| 412M/412M [00:01<00:00, 232MB/s]
-Downloading data:  36%|███▌      | 13/36 [00:32<00:45,  1.99s/files]
 data/train-00013-of-00036.parquet:   0%|          | 0.00/397M [00:00<?, ?B/s][A
-data/train-00013-of-00036.parquet:  13%|█▎        | 50.2M/397M [00:01<00:07, 49.4MB/s][A
-data/train-00013-of-00036.parquet: 100%|██████████| 397M/397M [00:01<00:00, 244MB/s]
-Downloading data:  39%|███▉      | 14/36 [00:33<00:41,  1.89s/files]
 data/train-00014-of-00036.parquet:   0%|          | 0.00/397M [00:00<?, ?B/s][A
-data/train-00014-of-00036.parquet:   7%|▋         | 28.6M/397M [00:01<00:12, 28.4MB/s][A
-data/train-00014-of-00036.parquet: 100%|██████████| 397M/397M [00:02<00:00, 209MB/s]  [A
-data/train-00014-of-00036.parquet: 100%|██████████| 397M/397M [00:02<00:00, 184MB/s]
-Downloading data:  42%|████▏     | 15/36 [00:36<00:41,  1.98s/files]
 data/train-00015-of-00036.parquet:   0%|          | 0.00/389M [00:00<?, ?B/s][A
-data/train-00015-of-00036.parquet:   8%|▊         | 29.7M/389M [00:01<00:12, 29.7MB/s][A
-data/train-00015-of-00036.parquet:  83%|████████▎ | 322M/389M [00:02<00:00, 152MB/s]  [A
-data/train-00015-of-00036.parquet: 100%|██████████| 389M/389M [00:02<00:00, 163MB/s]
-Downloading data:  44%|████▍     | 16/36 [00:38<00:42,  2.11s/files]
 data/train-00016-of-00036.parquet:   0%|          | 0.00/384M [00:00<?, ?B/s][A
-data/train-00016-of-00036.parquet:   7%|▋         | 27.0M/384M [00:01<00:13, 26.9MB/s][A
-data/train-00016-of-00036.parquet: 100%|██████████| 384M/384M [00:01<00:00, 208MB/s]
-Downloading data:  47%|████▋     | 17/36 [00:40<00:38,  2.04s/files]
 data/train-00017-of-00036.parquet:   0%|          | 0.00/441M [00:00<?, ?B/s][A
-data/train-00017-of-00036.parquet:   4%|▎         | 15.6M/441M [00:01<00:27, 15.6MB/s][A
-data/train-00017-of-00036.parquet: 100%|██████████| 441M/441M [00:02<00:00, 239MB/s]  [A
-data/train-00017-of-00036.parquet: 100%|██████████| 441M/441M [00:02<00:00, 207MB/s]
-Downloading data:  50%|█████     | 18/36 [00:42<00:37,  2.07s/files]
 data/train-00018-of-00036.parquet:   0%|          | 0.00/571M [00:00<?, ?B/s][A
-data/train-00018-of-00036.parquet:  10%|▉         | 56.0M/571M [00:01<00:09, 56.0MB/s][A
-data/train-00018-of-00036.parquet: 100%|██████████| 571M/571M [00:02<00:00, 244MB/s]  [A
-data/train-00018-of-00036.parquet: 100%|██████████| 571M/571M [00:02<00:00, 222MB/s]
-Downloading data:  53%|█████▎    | 19/36 [00:45<00:37,  2.23s/files]
 data/train-00019-of-00036.parquet:   0%|          | 0.00/413M [00:00<?, ?B/s][A
-data/train-00019-of-00036.parquet:  11%|█▏        | 47.0M/413M [00:01<00:07, 46.9MB/s][A
-data/train-00019-of-00036.parquet: 100%|██████████| 413M/413M [00:01<00:00, 230MB/s]
-Downloading data:  56%|█████▌    | 20/36 [00:46<00:33,  2.10s/files]
 data/train-00020-of-00036.parquet:   0%|          | 0.00/417M [00:00<?, ?B/s][A
-data/train-00020-of-00036.parquet:  11%|█         | 45.9M/417M [00:01<00:08, 45.9MB/s][A
-data/train-00020-of-00036.parquet: 100%|██████████| 417M/417M [00:01<00:00, 239MB/s]
-Downloading data:  58%|█████▊    | 21/36 [00:48<00:29,  2.00s/files]
 data/train-00021-of-00036.parquet:   0%|          | 0.00/401M [00:00<?, ?B/s][A
-data/train-00021-of-00036.parquet:   3%|▎         | 12.1M/401M [00:01<00:32, 12.1MB/s][A
-data/train-00021-of-00036.parquet: 100%|██████████| 401M/401M [00:02<00:00, 230MB/s]  [A
-data/train-00021-of-00036.parquet: 100%|██████████| 401M/401M [00:02<00:00, 197MB/s]
-Downloading data:  61%|██████    | 22/36 [00:50<00:28,  2.02s/files]
 data/train-00022-of-00036.parquet:   0%|          | 0.00/373M [00:00<?, ?B/s][A
-data/train-00022-of-00036.parquet:   7%|▋         | 26.8M/373M [00:01<00:12, 26.8MB/s][A
-data/train-00022-of-00036.parquet: 100%|██████████| 373M/373M [00:01<00:00, 214MB/s]
-Downloading data:  64%|██████▍   | 23/36 [00:52<00:25,  1.94s/files]
 data/train-00023-of-00036.parquet:   0%|          | 0.00/374M [00:00<?, ?B/s][A
-data/train-00023-of-00036.parquet:   4%|▍         | 16.5M/374M [00:01<00:21, 16.5MB/s][A
-data/train-00023-of-00036.parquet: 100%|██████████| 374M/374M [00:02<00:00, 214MB/s]  [A
-data/train-00023-of-00036.parquet: 100%|██████████| 374M/374M [00:02<00:00, 184MB/s]
-Downloading data:  67%|██████▋   | 24/36 [00:54<00:23,  1.97s/files]
 data/train-00024-of-00036.parquet:   0%|          | 0.00/531M [00:00<?, ?B/s][A
-data/train-00024-of-00036.parquet:   5%|▍         | 25.7M/531M [00:01<00:19, 25.4MB/s][A
-data/train-00024-of-00036.parquet: 100%|██████████| 531M/531M [00:02<00:00, 254MB/s]  [A
-data/train-00024-of-00036.parquet: 100%|██████████| 531M/531M [00:02<00:00, 225MB/s]
-Downloading data:  69%|██████▉   | 25/36 [00:56<00:23,  2.10s/files]
 data/train-00025-of-00036.parquet:   0%|          | 0.00/542M [00:00<?, ?B/s][A
-data/train-00025-of-00036.parquet:   4%|▍         | 23.1M/542M [00:01<00:22, 23.0MB/s][A
-data/train-00025-of-00036.parquet: 100%|██████████| 542M/542M [00:02<00:00, 241MB/s]  [A
-data/train-00025-of-00036.parquet: 100%|██████████| 542M/542M [00:02<00:00, 215MB/s]
-Downloading data:  72%|███████▏  | 26/36 [00:59<00:22,  2.23s/files]
 data/train-00026-of-00036.parquet:   0%|          | 0.00/434M [00:00<?, ?B/s][A
-data/train-00026-of-00036.parquet:  11%|█         | 47.0M/434M [00:01<00:08, 46.8MB/s][A
-data/train-00026-of-00036.parquet: 100%|██████████| 434M/434M [00:02<00:00, 219MB/s]  [A
-data/train-00026-of-00036.parquet: 100%|██████████| 434M/434M [00:02<00:00, 196MB/s]
-Downloading data:  75%|███████▌  | 27/36 [01:01<00:20,  2.23s/files]
 data/train-00027-of-00036.parquet:   0%|          | 0.00/366M [00:00<?, ?B/s][A
-data/train-00027-of-00036.parquet:  11%|█         | 38.9M/366M [00:01<00:08, 38.8MB/s][A
-data/train-00027-of-00036.parquet: 100%|██████████| 366M/366M [00:01<00:00, 186MB/s]
-Downloading data:  78%|███████▊  | 28/36 [01:03<00:17,  2.16s/files]
 data/train-00028-of-00036.parquet:   0%|          | 0.00/374M [00:00<?, ?B/s][A
-data/train-00028-of-00036.parquet:   9%|▊         | 32.5M/374M [00:01<00:10, 32.4MB/s][A
-data/train-00028-of-00036.parquet: 100%|██████████| 374M/374M [00:01<00:00, 230MB/s]
-Downloading data:  81%|████████  | 29/36 [01:05<00:14,  2.01s/files]
 data/train-00029-of-00036.parquet:   0%|          | 0.00/402M [00:00<?, ?B/s][A
-data/train-00029-of-00036.parquet:   8%|▊         | 30.8M/402M [00:01<00:12, 30.4MB/s][A
-data/train-00029-of-00036.parquet: 100%|██████████| 402M/402M [00:01<00:00, 241MB/s]
-Downloading data:  83%|████████▎ | 30/36 [01:06<00:11,  1.91s/files]
 data/train-00030-of-00036.parquet:   0%|          | 0.00/400M [00:00<?, ?B/s][A
-data/train-00030-of-00036.parquet:   0%|          | 34.0k/400M [00:01<3:39:09, 30.4kB/s][A
-data/train-00030-of-00036.parquet: 100%|██████████| 400M/400M [00:02<00:00, 192MB/s]    [A
-data/train-00030-of-00036.parquet: 100%|██████████| 400M/400M [00:02<00:00, 165MB/s]
-Downloading data:  86%|████████▌ | 31/36 [01:09<00:10,  2.07s/files]
 data/train-00031-of-00036.parquet:   0%|          | 0.00/382M [00:00<?, ?B/s][A
-data/train-00031-of-00036.parquet:   9%|▉         | 35.3M/382M [00:01<00:09, 35.2MB/s][A
-data/train-00031-of-00036.parquet: 100%|███��██████| 382M/382M [00:01<00:00, 243MB/s]
-Downloading data:  89%|████████▉ | 32/36 [01:11<00:07,  1.93s/files]
 data/train-00032-of-00036.parquet:   0%|          | 0.00/380M [00:00<?, ?B/s][A
-data/train-00032-of-00036.parquet:  10%|▉         | 37.3M/380M [00:01<00:09, 37.2MB/s][A
-data/train-00032-of-00036.parquet: 100%|██████████| 380M/380M [00:01<00:00, 214MB/s]
-Downloading data:  92%|█████████▏| 33/36 [01:12<00:05,  1.89s/files]
 data/train-00033-of-00036.parquet:   0%|          | 0.00/376M [00:00<?, ?B/s][A
-data/train-00033-of-00036.parquet:  19%|█▉        | 72.5M/376M [00:01<00:04, 72.5MB/s][A
-data/train-00033-of-00036.parquet: 100%|██████████| 376M/376M [00:01<00:00, 264MB/s]
-Downloading data:  94%|█████████▍| 34/36 [01:14<00:03,  1.76s/files]
 data/train-00034-of-00036.parquet:   0%|          | 0.00/372M [00:00<?, ?B/s][A
-data/train-00034-of-00036.parquet:  21%|██▏       | 79.7M/372M [00:01<00:03, 79.5MB/s][A
-data/train-00034-of-00036.parquet: 100%|██████████| 372M/372M [00:01<00:00, 262MB/s]
-Downloading data:  97%|█████████▋| 35/36 [01:15<00:01,  1.66s/files]
 data/train-00035-of-00036.parquet:   0%|          | 0.00/373M [00:00<?, ?B/s][A
-data/train-00035-of-00036.parquet:  11%|█         | 40.4M/373M [00:01<00:08, 40.4MB/s][A
-data/train-00035-of-00036.parquet: 100%|██████████| 373M/373M [00:01<00:00, 236MB/s]
-Downloading data: 100%|██████████| 36/36 [01:17<00:00,  1.64s/files]
-Downloading data: 100%|██████████| 36/36 [01:17<00:00,  2.15s/files]
 data/validation-00000-of-00001.parquet:   0%|          | 0.00/162M [00:00<?, ?B/s][A
-data/validation-00000-of-00001.parquet: 100%|██████████| 162M/162M [00:00<00:00, 180MB/s]
 data/test-00000-of-00001.parquet:   0%|          | 0.00/306M [00:00<?, ?B/s][A
-data/test-00000-of-00001.parquet:  28%|██▊       | 86.6M/306M [00:01<00:02, 86.5MB/s][A
-data/test-00000-of-00001.parquet: 100%|██████████| 306M/306M [00:01<00:00, 186MB/s]
 Generating train split:   0%|          | 0/145152 [00:00<?, ? examples/s][A
-Generating train split:   0%|          | 200/145152 [00:01<15:20, 157.53 examples/s][A
-Generating train split:   0%|          | 500/145152 [00:02<10:51, 221.87 examples/s][A
-Generating train split:   1%|          | 800/145152 [00:03<10:02, 239.78 examples/s][A
-Generating train split:   1%|          | 1100/145152 [00:04<09:50, 244.04 examples/s][A
-Generating train split:   1%|          | 1400/145152 [00:05<09:22, 255.55 examples/s][A
-Generating train split:   1%|          | 1700/145152 [00:06<09:10, 260.38 examples/s][A
-Generating train split:   1%|▏         | 2000/145152 [00:08<09:25, 253.28 examples/s][A
-Generating train split:   3%|▎         | 4132/145152 [00:09<03:02, 771.26 examples/s][A
-Generating train split:   4%|▍         | 6232/145152 [00:10<02:00, 1148.43 examples/s][A
-Generating train split:   6%|▌         | 8464/145152 [00:11<01:35, 1438.12 examples/s][A
-Generating train split:   7%|▋         | 10664/145152 [00:12<01:22, 1633.68 examples/s][A
-Generating train split:   9%|▉         | 13296/145152 [00:13<01:08, 1911.79 examples/s][A
-Generating train split:  11%|█         | 16228/145152 [00:14<00:58, 2200.47 examples/s][A
-Generating train split:  13%|█▎        | 19128/145152 [00:15<00:52, 2393.91 examples/s][A
-Generating train split:  15%|█▍        | 21560/145152 [00:16<00:58, 2099.48 examples/s][A
-Generating train split:  16%|█▋        | 23760/145152 [00:18<01:10, 1727.02 examples/s][A
-Generating train split:  18%|█▊        | 25692/145152 [00:20<01:16, 1559.13 examples/s][A
-Generating train split:  19%|█▉        | 27392/145152 [00:21<01:20, 1459.08 examples/s][A
-Generating train split:  20%|█▉        | 29024/145152 [00:23<01:23, 1384.79 examples/s][A
-Generating train split:  21%|██▏       | 31024/145152 [00:24<01:16, 1499.93 examples/s][A
-Generating train split:  23%|██▎       | 33056/145152 [00:25<01:10, 1592.63 examples/s][A
-Generating train split:  25%|██▍       | 36156/145152 [00:26<00:55, 1968.72 examples/s][A
-Generating train split:  27%|██▋       | 39488/145152 [00:27<00:45, 2327.28 examples/s][A
-Generating train split:  30%|██▉       | 43120/145152 [00:28<00:38, 2665.11 examples/s][A
-Generating train split:  32%|███��      | 46152/145152 [00:29<00:38, 2594.31 examples/s][A
-Generating train split:  34%|███▎      | 48984/145152 [00:30<00:37, 2539.77 examples/s][A
-Generating train split:  36%|███▌      | 51684/145152 [00:31<00:36, 2558.63 examples/s][A
-Generating train split:  38%|███▊      | 54516/145152 [00:32<00:35, 2557.69 examples/s][A
-Generating train split:  40%|███▉      | 57348/145152 [00:33<00:34, 2578.93 examples/s][A
-Generating train split:  42%|████▏     | 60348/145152 [00:35<00:31, 2654.64 examples/s][A
-Generating train split:  44%|████▎     | 63180/145152 [00:36<00:30, 2645.25 examples/s][A
-Generating train split:  45%|████▌     | 66012/145152 [00:37<00:29, 2693.35 examples/s][A
-Generating train split:  47%|████▋     | 68844/145152 [00:38<00:28, 2721.06 examples/s][A
-Generating train split:  49%|████▉     | 71644/145152 [00:39<00:27, 2672.98 examples/s][A
-Generating train split:  51%|█████     | 74376/145152 [00:40<00:30, 2317.29 examples/s][A
-Generating train split:  53%|█████▎    | 76908/145152 [00:42<00:31, 2184.76 examples/s][A
-Generating train split:  55%|█████▍    | 79608/145152 [00:43<00:28, 2311.93 examples/s][A
-Generating train split:  57%|█████▋    | 82440/145152 [00:44<00:26, 2387.58 examples/s][A
-Generating train split:  59%|█████▊    | 84972/145152 [00:45<00:24, 2425.11 examples/s][A
-Generating train split:  60%|██████    | 87672/145152 [00:46<00:23, 2488.68 examples/s][A
-Generating train split:  63%|██████▎   | 90804/145152 [00:47<00:20, 2600.22 examples/s][A
-Generating train split:  65%|██████▍   | 93636/145152 [00:48<00:19, 2647.10 examples/s][A
-Generating train split:  67%|██████▋   | 96636/145152 [00:49<00:17, 2736.00 examples/s][A
-Generating train split:  69%|██████▊   | 99468/145152 [00:50<00:18, 2451.68 examples/s][A
-Generating train split:  70%|███████   | 102000/145152 [00:52<00:18, 2286.07 examples/s][A
-Generating train split:  72%|███████▏  | 104400/145152 [00:53<00:18, 2174.25 examples/s][A
-Generating train split:  74%|███████▎  | 106832/145152 [00:54<00:17, 2171.99 examples/s][A
-Generating train split:  76%|███████▌  | 109764/145152 [00:55<00:15, 2346.25 examples/s][A
-Generating train split:  78%|███████▊  | 112996/145152 [00:56<00:12, 2520.70 examples/s][A
-Generating train split:  80%|███████▉  | 115896/145152 [00:57<00:11, 2609.96 examples/s][A
-Generating train split:  82%|████████▏ | 118728/145152 [00:58<00:10, 2637.69 examples/s][A
-Generating train split:  84%|████████▎ | 121560/145152 [00:59<00:08, 2641.89 examples/s][A
-Generating train split:  86%|████████▌ | 124260/145152 [01:00<00:07, 2635.13 examples/s][A
-Generating train split:  88%|████████▊ | 127092/145152 [01:01<00:06, 2629.63 examples/s][A
-Generating train split:  90%|████████▉ | 129924/145152 [01:02<00:05, 2660.36 examples/s][A
-Generating train split:  92%|█████████▏| 132924/145152 [01:03<00:04, 2716.41 examples/s][A
-Generating train split:  94%|█████████▎| 135756/145152 [01:05<00:03, 2701.85 examples/s][A
-Generating train split:  95%|█████████▌| 138588/145152 [01:06<00:02, 2720.17 examples/s][A
-Generating train split:  97%|█████████▋| 141420/145152 [01:07<00:01, 2729.46 examples/s][A
-Generating train split:  99%|█████████▉| 144420/145152 [01:08<00:00, 2724.12 examples/s][A
-Generating train split: 100%|██████████| 145152/145152 [01:08<00:00, 2123.32 examples/s]
 Generating validation split:   0%|          | 0/239 [00:00<?, ? examples/s][A
-Generating validation split: 100%|██████████| 239/239 [00:00<00:00, 266.52 examples/s]
 Generating test split:   0%|          | 0/418 [00:00<?, ? examples/s][A
-Generating test split:  48%|████▊     | 200/418 [00:01<00:01, 162.76 examples/s][A
-Generating test split: 100%|██████████| 418/418 [00:01<00:00, 249.39 examples/s]
 Traceback (most recent call last):
-  File "/app/chatterbox-multilingual-finetuning/src/finetune_t3.py", line 571, in <module>
     main()
     ~~~~^^
-  File "/app/chatterbox-multilingual-finetuning/src/finetune_t3.py", line 528, in main
-    chatterbox_model = ChatterboxMultilingualTTS()
-TypeError: ChatterboxMultilingualTTS.__init__() missing 4 required positional arguments: 't3', 's3gen', 've', and 'tokenizer'

 - output_dir: /app/checkpoints/v1
 Starting training...
+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 06:36:53 - 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,
+adam_epsilon=1e-08,
+auto_find_batch_size=False,
+average_tokens_across_devices=True,
+batch_eval_metrics=False,
+bf16=False,
+bf16_full_eval=False,
+data_seed=None,
+dataloader_drop_last=False,
+dataloader_num_workers=8,
+dataloader_persistent_workers=False,
+dataloader_pin_memory=False,
+dataloader_prefetch_factor=None,
+ddp_backend=None,
+ddp_broadcast_buffers=None,
+ddp_bucket_cap_mb=None,
+ddp_find_unused_parameters=None,
+ddp_timeout=1800,
+debug=[],
+deepspeed=None,
+disable_tqdm=False,
+do_eval=True,
+do_predict=False,
+do_train=True,
+early_stopping_patience=None,
+enable_jit_checkpoint=False,
+eval_accumulation_steps=None,
+eval_delay=0,
+eval_do_concat_batches=True,
+eval_on_start=True,
+eval_steps=2,
+eval_strategy=IntervalStrategy.STEPS,
+eval_use_gather_object=False,
+fp16=True,
+fp16_full_eval=False,
+fsdp=[],
+fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False},
+full_determinism=False,
+gradient_accumulation_steps=1,
+gradient_checkpointing=False,
+gradient_checkpointing_kwargs=None,
+greater_is_better=None,
+group_by_length=False,
+hub_always_push=False,
+hub_model_id=None,
+hub_private_repo=None,
+hub_revision=None,
+hub_strategy=HubStrategy.EVERY_SAVE,
+hub_token=<HUB_TOKEN>,
+ignore_data_skip=False,
+include_for_metrics=[],
+include_num_input_tokens_seen=no,
+label_names=['labels_speech'],
+label_smoothing_factor=0.0,
+learning_rate=5e-05,
+length_column_name=length,
+liger_kernel_config=None,
+load_best_model_at_end=False,
+local_rank=-1,
+log_level=passive,
+log_level_replica=warning,
+log_on_each_node=True,
+logging_dir=None,
+logging_first_step=False,
+logging_nan_inf_filter=True,
+logging_steps=1.0,
+logging_strategy=IntervalStrategy.STEPS,
+lr_scheduler_kwargs=None,
+lr_scheduler_type=SchedulerType.LINEAR,
+max_grad_norm=1.0,
+max_steps=-1,
+metric_for_best_model=None,
+neftune_noise_alpha=None,
+num_train_epochs=1.0,
+optim=OptimizerNames.ADAMW_TORCH_FUSED,
+optim_args=None,
+optim_target_modules=None,
+output_dir=/app/checkpoints/v1,
+parallelism_config=None,
+per_device_eval_batch_size=8,
+per_device_train_batch_size=1,
+prediction_loss_only=False,
+project=huggingface,
+push_to_hub=False,
+remove_unused_columns=True,
+report_to=['tensorboard'],
+restore_callback_states_from_checkpoint=False,
+resume_from_checkpoint=None,
+run_name=None,
+save_on_each_node=False,
+save_only_model=False,
+save_steps=1.0,
+save_strategy=SaveStrategy.STEPS,
+save_total_limit=1,
+seed=42,
+skip_memory_metrics=True,
+tf32=None,
+torch_compile=False,
+torch_compile_backend=None,
+torch_compile_mode=None,
+torch_empty_cache_steps=None,
+trackio_space_id=trackio,
+use_cache=False,
+use_cpu=False,
+use_liger_kernel=False,
+warmup_ratio=None,
+warmup_steps=1.0,
+weight_decay=0.0,
+)
+02/07/2026 06:36:53 - 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)
+02/07/2026 06:36:53 - 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='transcript', 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 06:36:53 - INFO - __main__ - Loading ChatterboxTTS model...
+02/07/2026 06:36:53 - INFO - __main__ - Loading model from Hugging Face Hub: /app/hf_cache/models--ResembleAI--chatterbox/snapshots/05e904af2b5c7f8e482687a9d7336c5c824467d9
+02/07/2026 06:36:53 - 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..
+02/07/2026 06:36:53 - 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..
+02/07/2026 06:36:53 - 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..
+02/07/2026 06:36:53 - 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..
+02/07/2026 06:36:53 - INFO - __main__ - conds.pt not found on Hub or failed to download for this model.
+02/07/2026 06:36:53 - 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][A
+Fetching 5 files:   0%|          | 0/5 [00:00<?, ?it/s][A02/07/2026 06:36:53 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/ResembleAI/chatterbox/resolve/05e904af2b5c7f8e482687a9d7336c5c824467d9/conds.pt "HTTP/1.1 302 Found"
+02/07/2026 06:36:53 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/ResembleAI/chatterbox/resolve/05e904af2b5c7f8e482687a9d7336c5c824467d9/s3gen.pt "HTTP/1.1 302 Found"
+02/07/2026 06:36:53 - 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 06:36:53 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/ResembleAI/chatterbox/resolve/05e904af2b5c7f8e482687a9d7336c5c824467d9/t3_mtl23ls_v2.safetensors "HTTP/1.1 302 Found"
+02/07/2026 06:36:53 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/ResembleAI/chatterbox/resolve/05e904af2b5c7f8e482687a9d7336c5c824467d9/ve.pt "HTTP/1.1 302 Found"
+02/07/2026 06:36:53 - 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 06:36:53 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/models/ResembleAI/chatterbox/xet-read-token/05e904af2b5c7f8e482687a9d7336c5c824467d9 "HTTP/1.1 200 OK"
+Downloading (incomplete total...):   0%|          | 0.00/1.06G [00:00<?, ?B/s][A02/07/2026 06:36:53 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/models/ResembleAI/chatterbox/xet-read-token/05e904af2b5c7f8e482687a9d7336c5c824467d9 "HTTP/1.1 200 OK"
+Downloading (incomplete total...):   0%|          | 0.00/1.06G [00:00<?, ?B/s][A02/07/2026 06:36:53 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/models/ResembleAI/chatterbox/xet-read-token/05e904af2b5c7f8e482687a9d7336c5c824467d9 "HTTP/1.1 200 OK"
+02/07/2026 06:36:53 - 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%|          | 0.00/1.06G [00:00<?, ?B/s][A
+Downloading (incomplete total...):   0%|          | 0.00/1.06G [00:00<?, ?B/s][A02/07/2026 06:36:53 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/models/ResembleAI/chatterbox/xet-read-token/05e904af2b5c7f8e482687a9d7336c5c824467d9 "HTTP/1.1 200 OK"
+Downloading (incomplete total...):   0%|          | 70.0k/3.21G [00:00<53:33, 998kB/s][A
+Downloading (incomplete total...):   0%|          | 13.5M/3.21G [00:02<09:29, 5.60MB/s][A
+Downloading (incomplete total...):   2%|▏         | 64.6M/3.21G [00:09<07:22, 7.10MB/s][A
+Downloading (incomplete total...):   4%|▍         | 132M/3.21G [00:11<03:46, 13.6MB/s] [A
+Downloading (incomplete total...):  17%|█▋        | 543M/3.21G [00:12<00:36, 72.6MB/s][A
+Downloading (incomplete total...):  54%|█████▍    | 1.73G/3.21G [00:13<00:05, 269MB/s][A
+Fetching 5 files:  60%|██████    | 3/5 [00:13<00:09,  4.60s/it][A
+Fetching 5 files: 100%|██████████| 5/5 [00:14<00:00,  2.87s/it]
+Download complete: 100%|██████████| 3.21G/3.21G [00:14<00:00, 269MB/s]                [A
+Download complete: 100%|██████████| 3.21G/3.21G [00:21<00:00, 147MB/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 06:37:16 - INFO - root - input frame rate=25
+02/07/2026 06:37:21 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/ResembleAI/chatterbox/resolve/main/Cangjie5_TC.json "HTTP/1.1 307 Temporary Redirect"
+02/07/2026 06:37:21 - 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 06:37:21 - 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][A
+Cangjie5_TC.json: 100%|██████████| 1.92M/1.92M [00:00<00:00, 85.4MB/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][A
+100%|██████████| 34567143/34567143 [00:00<00:00, 212189576.69it/s]
+02/07/2026 06:37:23 - INFO - __main__ - Voice Encoder frozen.
+02/07/2026 06:37:23 - INFO - __main__ - S3Gen model frozen.
+02/07/2026 06:37:23 - INFO - __main__ - T3 model set to trainable.
+02/07/2026 06:37:23 - INFO - __main__ - Loading and processing dataset...
+02/07/2026 06:37:23 - INFO - __main__ - Loading dataset 'rahul7star/hindi-speech-dataset' from Hugging Face Hub.
+02/07/2026 06:37:23 - 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 06:37:23 - 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 06:37:23 - 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][A
+README.md: 100%|██████████| 591/591 [00:00<00:00, 2.57MB/s]
+02/07/2026 06:37:23 - 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 06:37:23 - 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 06:37:23 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/datasets/rahul7star/hindi-speech-dataset/revision/0bfd5e2e4555ec80d7dd74b10442836d2e169be6 "HTTP/1.1 200 OK"
+02/07/2026 06:37:23 - 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 06:37:24 - INFO - httpx - HTTP Request: GET https://datasets-server.huggingface.co/info?dataset=rahul7star/hindi-speech-dataset "HTTP/1.1 200 OK"
+02/07/2026 06:37:24 - 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 06:37:24 - 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 06:37:24 - 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 06:37:24 - 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 06:37:24 - 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][A
+data/train-00000-of-00036.parquet:   1%|          | 17.0M/1.77G [00:01<01:43, 16.9MB/s][A
+data/train-00000-of-00036.parquet:  22%|██▏       | 387M/1.77G [00:02<00:06, 223MB/s]  [A
+data/train-00000-of-00036.parquet:  44%|████▍     | 780M/1.77G [00:03<00:03, 299MB/s][A
+data/train-00000-of-00036.parquet:  64%|██████▍   | 1.14G/1.77G [00:04<00:01, 321MB/s][A
+data/train-00000-of-00036.parquet:  92%|█████████▏| 1.63G/1.77G [00:05<00:00, 370MB/s][A
+data/train-00000-of-00036.parquet: 100%|██████████| 1.77G/1.77G [00:05<00:00, 333MB/s]
+Downloading data:   3%|▎         | 1/36 [00:05<03:06,  5.34s/files]02/07/2026 06:37:29 - 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][A
+data/train-00001-of-00036.parquet:   9%|▊         | 42.2M/496M [00:01<00:10, 42.2MB/s][A
+data/train-00001-of-00036.parquet: 100%|██████████| 496M/496M [00:01<00:00, 252MB/s]
+Downloading data:   6%|▌         | 2/36 [00:07<01:54,  3.38s/files]02/07/2026 06:37:31 - 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][A
+data/train-00002-of-00036.parquet:   6%|▋         | 29.1M/461M [00:01<00:14, 29.1MB/s][A
+data/train-00002-of-00036.parquet: 100%|██████████| 461M/461M [00:01<00:00, 259MB/s]
+Downloading data:   8%|▊         | 3/36 [00:09<01:27,  2.66s/files]02/07/2026 06:37:33 - 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][A
+data/train-00003-of-00036.parquet:   6%|▌         | 22.2M/372M [00:01<00:15, 22.1MB/s][A
+data/train-00003-of-00036.parquet: 100%|██████████| 372M/372M [00:01<00:00, 197MB/s]
+Downloading data:  11%|█         | 4/36 [00:11<01:15,  2.36s/files]02/07/2026 06:37:35 - 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][A
+data/train-00004-of-00036.parquet:  14%|█▍        | 51.9M/373M [00:01<00:06, 51.9MB/s][A
+data/train-00004-of-00036.parquet: 100%|██████████| 373M/373M [00:01<00:00, 234MB/s]
+Downloading data:  14%|█▍        | 5/36 [00:12<01:04,  2.09s/files]02/07/2026 06:37:36 - 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][A
+data/train-00005-of-00036.parquet:   1%|          | 9.69M/841M [00:01<01:25, 9.68MB/s][A
+data/train-00005-of-00036.parquet:  29%|██▉       | 245M/841M [00:02<00:04, 142MB/s]  [A
+data/train-00005-of-00036.parquet: 100%|██████████| 841M/841M [00:03<00:00, 288MB/s][A
+data/train-00005-of-00036.parquet: 100%|██████████| 841M/841M [00:03<00:00, 242MB/s]
+Downloading data:  17%|█▋        | 6/36 [00:16<01:17,  2.57s/files]02/07/2026 06:37:40 - 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][A
+data/train-00006-of-00036.parquet:   4%|▎         | 29.3M/837M [00:01<00:27, 29.3MB/s][A
+data/train-00006-of-00036.parquet:  44%|████▍     | 366M/837M [00:02<00:02, 210MB/s]  [A
+data/train-00006-of-00036.parquet: 100%|██████████| 837M/837M [00:03<00:00, 323MB/s][A
+data/train-00006-of-00036.parquet: 100%|██████████| 837M/837M [00:03<00:00, 275MB/s]
+Downloading data:  19%|█▉        | 7/36 [00:19<01:19,  2.73s/files]02/07/2026 06:37:43 - 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][A
+data/train-00007-of-00036.parquet:   6%|▌         | 35.0M/618M [00:01<00:16, 34.9MB/s][A
+data/train-00007-of-00036.parquet:  72%|███████▏  | 447M/618M [00:02<00:00, 256MB/s]  [A
+data/train-00007-of-00036.parquet: 100%|██████████| 618M/618M [00:02<00:00, 222MB/s]
+Downloading data:  22%|██▏       | 8/36 [00:22<01:17,  2.76s/files]02/07/2026 06:37:46 - 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][A
+data/train-00008-of-00036.parquet:   9%|▉         | 37.5M/415M [00:01<00:10, 36.9MB/s][A
+data/train-00008-of-00036.parquet: 100%|██████████| 415M/415M [00:01<00:00, 253MB/s]
+Downloading data:  25%|██▌       | 9/36 [00:23<01:05,  2.42s/files]02/07/2026 06:37:47 - 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][A
+data/train-00009-of-00036.parquet:  14%|█▍        | 43.7M/303M [00:01<00:05, 43.7MB/s][A
+data/train-00009-of-00036.parquet: 100%|██████████| 303M/303M [00:01<00:00, 212MB/s]
+Downloading data:  28%|██▊       | 10/36 [00:25<00:55,  2.12s/files]02/07/2026 06:37:49 - 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][A
+data/train-00010-of-00036.parquet:  25%|██▍       | 84.7M/341M [00:01<00:03, 84.6MB/s][A
+data/train-00010-of-00036.parquet: 100%|██████████| 341M/341M [00:01<00:00, 189MB/s]
+Downloading data:  31%|███       | 11/36 [00:27<00:50,  2.04s/files]02/07/2026 06:37:51 - 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][A
+data/train-00011-of-00036.parquet:   7%|▋         | 29.0M/440M [00:01<00:14, 28.9MB/s][A
+data/train-00011-of-00036.parquet: 100%|██████████| 440M/440M [00:01<00:00, 224MB/s]
+Downloading data:  33%|███▎      | 12/36 [00:29<00:48,  2.03s/files]02/07/2026 06:37:53 - 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][A
+data/train-00012-of-00036.parquet:  16%|█▌        | 65.2M/412M [00:01<00:05, 65.1MB/s][A
+data/train-00012-of-00036.parquet: 100%|██████████| 412M/412M [00:01<00:00, 256MB/s]
+Downloading data:  36%|███▌      | 13/36 [00:30<00:43,  1.91s/files]02/07/2026 06:37:54 - 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][A
+data/train-00013-of-00036.parquet:   6%|▌         | 24.0M/397M [00:01<00:15, 24.0MB/s][A
+data/train-00013-of-00036.parquet: 100%|██████████| 397M/397M [00:01<00:00, 218MB/s]
+Downloading data:  39%|███▉      | 14/36 [00:32<00:41,  1.89s/files]02/07/2026 06:37:56 - 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][A
+data/train-00014-of-00036.parquet:   7%|▋         | 27.8M/397M [00:01<00:13, 27.8MB/s][A
+data/train-00014-of-00036.parquet: 100%|██████████| 397M/397M [00:01<00:00, 202MB/s]
+Downloading data:  42%|████▏     | 15/36 [00:34<00:40,  1.92s/files]02/07/2026 06:37:58 - 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][A
+data/train-00015-of-00036.parquet:   6%|▌         | 23.7M/389M [00:01<00:15, 23.7MB/s][A
+data/train-00015-of-00036.parquet: 100%|██████████| 389M/389M [00:02<00:00, 206MB/s]  [A
+data/train-00015-of-00036.parquet: 100%|██████████| 389M/389M [00:02<00:00, 181MB/s]
+Downloading data:  44%|████▍     | 16/36 [00:36<00:39,  2.00s/files]02/07/2026 06:38:00 - 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][A
+data/train-00016-of-00036.parquet:   8%|▊         | 30.8M/384M [00:01<00:11, 30.6MB/s][A
+data/train-00016-of-00036.parquet: 100%|██████████| 384M/384M [00:02<00:00, 191MB/s]
+Downloading data:  47%|████▋     | 17/36 [00:38<00:38,  2.01s/files]02/07/2026 06:38:02 - 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][A
+data/train-00017-of-00036.parquet:   4%|▍         | 19.7M/441M [00:01<00:21, 19.7MB/s][A
+data/train-00017-of-00036.parquet: 100%|██████████| 441M/441M [00:02<00:00, 230MB/s]  [A
+data/train-00017-of-00036.parquet: 100%|██████████| 441M/441M [00:02<00:00, 201MB/s]
+Downloading data:  50%|█████     | 18/36 [00:40<00:37,  2.07s/files]02/07/2026 06:38:05 - 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][A
+data/train-00018-of-00036.parquet:   4%|▍         | 24.4M/571M [00:01<00:22, 24.3MB/s][A
+data/train-00018-of-00036.parquet: 100%|██████████| 571M/571M [00:02<00:00, 228MB/s]  [A
+data/train-00018-of-00036.parquet: 100%|██████████| 571M/571M [00:02<00:00, 206MB/s]
+Downloading data:  53%|█████▎    | 19/36 [00:43<00:38,  2.29s/files]02/07/2026 06:38:07 - 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][A
+data/train-00019-of-00036.parquet:  14%|█▍        | 56.8M/413M [00:01<00:06, 56.1MB/s][A
+data/train-00019-of-00036.parquet: 100%|██████████| 413M/413M [00:01<00:00, 216MB/s]
+Downloading data:  56%|█████▌    | 20/36 [00:45<00:34,  2.18s/files]02/07/2026 06:38:09 - 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][A
+data/train-00020-of-00036.parquet:   7%|▋         | 27.2M/417M [00:01<00:14, 27.2MB/s][A
+data/train-00020-of-00036.parquet: 100%|██████████| 417M/417M [00:02<00:00, 238MB/s]  [A
+data/train-00020-of-00036.parquet: 100%|██████████| 417M/417M [00:02<00:00, 207MB/s]
+Downloading data:  58%|█████▊    | 21/36 [00:47<00:32,  2.14s/files]02/07/2026 06:38:11 - 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][A
+data/train-00021-of-00036.parquet:  12%|█▏        | 48.2M/401M [00:01<00:07, 48.1MB/s][A
+data/train-00021-of-00036.parquet: 100%|██████████| 401M/401M [00:01<00:00, 206MB/s]
+Downloading data:  61%|██████    | 22/36 [00:49<00:29,  2.09s/files]02/07/2026 06:38:13 - 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][A
+data/train-00022-of-00036.parquet:   8%|▊         | 29.0M/373M [00:01<00:11, 29.0MB/s][A
+data/train-00022-of-00036.parquet: 100%|██████████| 373M/373M [00:01<00:00, 223MB/s]
+Downloading data:  64%|██████▍   | 23/36 [00:51<00:25,  1.97s/files]02/07/2026 06:38:15 - 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][A
+data/train-00023-of-00036.parquet:   4%|▍         | 14.4M/374M [00:01<00:24, 14.4MB/s][A
+data/train-00023-of-00036.parquet: 100%|██████████| 374M/374M [00:01<00:00, 192MB/s]
+Downloading data:  67%|██████▋   | 24/36 [00:53<00:23,  1.97s/files]02/07/2026 06:38:17 - 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][A
+data/train-00024-of-00036.parquet:   7%|▋         | 38.8M/531M [00:01<00:12, 38.7MB/s][A
+data/train-00024-of-00036.parquet: 100%|██████████| 531M/531M [00:02<00:00, 238MB/s]  [A
+data/train-00024-of-00036.parquet: 100%|██████████| 531M/531M [00:02<00:00, 214MB/s]
+Downloading data:  69%|██████▉   | 25/36 [00:55<00:23,  2.14s/files]02/07/2026 06:38:20 - 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][A
+data/train-00025-of-00036.parquet:   4%|▎         | 19.5M/542M [00:01<00:26, 19.4MB/s][A
+data/train-00025-of-00036.parquet:  87%|████████▋ | 469M/542M [00:02<00:00, 272MB/s]  [A
+data/train-00025-of-00036.parquet: 100%|██████████| 542M/542M [00:02<00:00, 193MB/s]
+Downloading data:  72%|███████▏  | 26/36 [00:58<00:23,  2.35s/files]02/07/2026 06:38:22 - 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][A
+data/train-00026-of-00036.parquet:   7%|▋         | 28.3M/434M [00:01<00:14, 28.3MB/s][A
+data/train-00026-of-00036.parquet: 100%|██████████| 434M/434M [00:01<00:00, 219MB/s]
+Downloading data:  75%|███████▌  | 27/36 [01:00<00:20,  2.25s/files]02/07/2026 06:38:24 - 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][A
+data/train-00027-of-00036.parquet:   4%|▍         | 15.4M/366M [00:01<00:22, 15.4MB/s][A
+data/train-00027-of-00036.parquet: 100%|██████████| 366M/366M [00:01<00:00, 207MB/s]
+Downloading data:  78%|███████▊  | 28/36 [01:02<00:16,  2.11s/files]02/07/2026 06:38:26 - 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][A
+data/train-00028-of-00036.parquet:   6%|▌         | 21.6M/374M [00:01<00:16, 21.5MB/s][A
+data/train-00028-of-00036.parquet: 100%|██████████| 374M/374M [00:01<00:00, 207MB/s]
+Downloading data:  81%|████████  | 29/36 [01:04<00:14,  2.03s/files]02/07/2026 06:38:28 - 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][A
+data/train-00029-of-00036.parquet:  15%|█▌        | 60.5M/402M [00:01<00:05, 60.2MB/s][A
+data/train-00029-of-00036.parquet: 100%|██████████| 402M/402M [00:01<00:00, 226MB/s]
+Downloading data:  83%|████████▎ | 30/36 [01:06<00:11,  1.96s/files]02/07/2026 06:38:30 - 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][A
+data/train-00030-of-00036.parquet:   3%|▎         | 12.4M/400M [00:01<00:31, 12.2MB/s][A
+data/train-00030-of-00036.parquet: 100%|██████████| 400M/400M [00:02<00:00, 206MB/s]  [A
+data/train-00030-of-00036.parquet: 100%|██████████| 400M/400M [00:02<00:00, 180MB/s]
+Downloading data:  86%|████████▌ | 31/36 [01:08<00:10,  2.04s/files]02/07/2026 06:38:32 - 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][A
+data/train-00031-of-00036.parquet:   4%|▍         | 16.7M/382M [00:01<00:21, 16.7MB/s][A
+data/train-00031-of-00036.parquet: 100%|██████████| 382M/382M [00:01<00:00, 219MB/s]
+Downloading data:  89%|████████▉ | 32/36 [01:10<00:07,  1.96s/files]02/07/2026 06:38:34 - 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][A
+data/train-00032-of-00036.parquet:   6%|▌         | 21.5M/380M [00:01<00:16, 21.3MB/s][A
+data/train-00032-of-00036.parquet: 100%|██████████| 380M/380M [00:01<00:00, 204MB/s]
+Downloading data:  92%|█████████▏| 33/36 [01:12<00:05,  1.94s/files]02/07/2026 06:38:36 - 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][A
+data/train-00033-of-00036.parquet:   6%|▌         | 21.1M/376M [00:01<00:16, 21.0MB/s][A
+data/train-00033-of-00036.parquet: 100%|██████████| 376M/376M [00:01<00:00, 218MB/s]
+Downloading data:  94%|█████████▍| 34/36 [01:13<00:03,  1.89s/files]02/07/2026 06:38:38 - 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][A
+data/train-00034-of-00036.parquet:   9%|▉         | 34.9M/372M [00:01<00:09, 34.8MB/s][A
+data/train-00034-of-00036.parquet: 100%|██████████| 372M/372M [00:01<00:00, 208MB/s]
+Downloading data:  97%|█████████▋| 35/36 [01:15<00:01,  1.86s/files]02/07/2026 06:38:39 - 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][A
+data/train-00035-of-00036.parquet:   1%|          | 3.49M/373M [00:01<01:46, 3.47MB/s][A
+data/train-00035-of-00036.parquet:  76%|███████▋  | 284M/373M [00:02<00:00, 166MB/s]  [A
+data/train-00035-of-00036.parquet: 100%|██████████| 373M/373M [00:02<00:00, 171MB/s]
+Downloading data: 100%|██████████| 36/36 [01:17<00:00,  1.96s/files]
+Downloading data: 100%|██████████| 36/36 [01:17<00:00,  2.16s/files]
+02/07/2026 06:38:42 - 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][A
+data/validation-00000-of-00001.parquet: 100%|██████████| 162M/162M [00:00<00:00, 170MB/s]
+02/07/2026 06:38:43 - 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][A
+data/test-00000-of-00001.parquet:  10%|█         | 32.0M/306M [00:01<00:08, 32.0MB/s][A
+data/test-00000-of-00001.parquet: 100%|██████████| 306M/306M [00:01<00:00, 162MB/s]
 Generating train split:   0%|          | 0/145152 [00:00<?, ? examples/s][A
+Generating train split:   0%|          | 200/145152 [00:01<16:42, 144.63 examples/s][A
+Generating train split:   0%|          | 500/145152 [00:02<11:32, 208.82 examples/s][A
+Generating train split:   1%|          | 800/145152 [00:03<10:57, 219.41 examples/s][A
+Generating train split:   1%|          | 1100/145152 [00:05<10:22, 231.39 examples/s][A
+Generating train split:   1%|          | 1400/145152 [00:06<09:52, 242.62 examples/s][A
+Generating train split:   1%|          | 1700/145152 [00:07<10:14, 233.37 examples/s][A
+Generating train split:   1%|▏         | 2000/145152 [00:08<10:16, 232.11 examples/s][A
+Generating train split:   3%|▎         | 4132/145152 [00:09<03:18, 711.98 examples/s][A
+Generating train split:   4%|▍         | 6232/145152 [00:11<02:10, 1065.50 examples/s][A
+Generating train split:   6%|▌         | 8264/145152 [00:12<01:43, 1323.45 examples/s][A
+Generating train split:   7%|▋         | 10464/145152 [00:13<01:26, 1554.42 examples/s][A
+Generating train split:   9%|▉         | 12996/145152 [00:14<01:12, 1829.18 examples/s][A
+Generating train split:  11%|█         | 15996/145152 [00:15<01:00, 2145.75 examples/s][A
+Generating train split:  13%|█▎        | 18828/145152 [00:16<00:55, 2276.32 examples/s][A
+Generating train split:  15%|█▍        | 21160/145152 [00:17<01:00, 2043.95 examples/s][A
+Generating train split:  16%|█▌        | 23360/145152 [00:19<01:15, 1611.33 examples/s][A
+Generating train split:  17%|█▋        | 25192/145152 [00:21<01:22, 1459.91 examples/s][A
+Generating train split:  18%|█▊        | 26792/145152 [00:24<01:59, 991.25 examples/s] [A
+Generating train split:  19%|█▉        | 28092/145152 [00:28<02:44, 712.19 examples/s][A
+Generating train split:  20%|██        | 29424/145152 [00:29<02:24, 801.97 examples/s][A
+Generating train split:  22%|██▏       | 31424/145152 [00:30<01:54, 991.92 examples/s][A
+Generating train split:  23%|██▎       | 33456/145152 [00:31<01:35, 1174.48 examples/s][A
+Generating train split:  25%|██▌       | 36688/145152 [00:32<01:07, 1601.04 examples/s][A
+Generating train split:  28%|██▊       | 40420/145152 [00:33<00:50, 2079.51 examples/s][A
+Generating train split:  30%|███       | 43720/145152 [00:34<00:42, 2365.48 examples/s][A
+Generating train split:  32%|███▏      | 46452/145152 [00:35<00:41, 2390.53 examples/s][A
+Generating train split:  34%|███▍      | 49284/145152 [00:36<00:40, 2361.13 examples/s][A
+Generating train split:  36%|███▌      | 52284/145152 [00:38<00:37, 2488.41 examples/s][A
+Generating train split:  38%|███▊      | 55116/145152 [00:39<00:35, 2515.75 examples/s][A
+Generating train split:  40%|███▉      | 57948/145152 [00:40<00:33, 2569.15 examples/s][A
+Generating train split:  42%|████▏     | 60780/145152 [00:41<00:32, 2608.73 examples/s][A
+Generating train split:  44%|████▍     | 63780/145152 [00:42<00:30, 2669.10 examples/s][A
+Generating train split:  46%|████▌     | 66612/145152 [00:43<00:29, 2693.82 examples/s][A
+Generating train split:  48%|████▊     | 69444/145152 [00:44<00:27, 2716.87 examples/s][A
+Generating train split:  50%|████▉     | 72244/145152 [00:45<00:27, 2622.81 examples/s][A
+Generating train split:  52%|█████▏    | 74976/145152 [00:46<00:29, 2355.73 examples/s][A
+Generating train split:  53%|█████▎    | 77508/145152 [00:48<00:29, 2286.13 examples/s][A
+Generating train split:  55%|█████▌    | 80208/145152 [00:49<00:27, 2370.14 examples/s][A
+Generating train split:  57%|█████▋    | 83040/145152 [00:50<00:25, 2430.30 examples/s][A
+Generating train split:  59%|█████▉    | 85872/145152 [00:51<00:23, 2470.58 examples/s][A
+Generating train split:  61%|██████    | 88804/145152 [00:52<00:22, 2556.50 examples/s][A
+Generating train split:  63%|██████▎   | 91704/145152 [00:53<00:20, 2602.06 examples/s][A
+Generating train split:  65%|██████▌   | 94836/145152 [00:54<00:18, 2675.90 examples/s][A
+Generating train split:  67%|██████▋   | 97668/145152 [00:55<00:17, 2650.98 examples/s][A
+Generating train split:  69%|██████▉   | 100468/145152 [00:57<00:18, 2413.16 examples/s][A
+Generating train split:  71%|███████   | 103000/145152 [00:58<00:18, 2278.09 examples/s][A
+Generating train split:  73%|███████▎  | 105432/145152 [00:59<00:18, 2178.09 examples/s][A
+Generating train split:  75%|███████▍  | 108332/145152 [01:00<00:15, 2304.88 examples/s][A
+Generating train split:  77%|��██████▋  | 111264/145152 [01:01<00:13, 2464.87 examples/s][A
+Generating train split:  79%|███████▉  | 114396/145152 [01:02<00:11, 2599.16 examples/s][A
+Generating train split:  81%|████████  | 117228/145152 [01:03<00:10, 2637.74 examples/s][A
+Generating train split:  83%|████████▎ | 119928/145152 [01:04<00:09, 2650.37 examples/s][A
+Generating train split:  85%|████████▍ | 122760/145152 [01:05<00:08, 2659.21 examples/s][A
+Generating train split:  87%|████████▋ | 125592/145152 [01:06<00:07, 2661.61 examples/s][A
+Generating train split:  89%|████████▊ | 128592/145152 [01:08<00:06, 2719.21 examples/s][A
+Generating train split:  91%|█████████ | 131424/145152 [01:09<00:05, 2744.68 examples/s][A
+Generating train split:  92%|█████████▏| 134256/145152 [01:10<00:03, 2752.94 examples/s][A
+Generating train split:  95%|█████████▍| 137188/145152 [01:11<00:02, 2782.20 examples/s][A
+Generating train split:  97%|█████████▋| 140088/145152 [01:12<00:01, 2787.69 examples/s][A
+Generating train split:  99%|█████████▊| 143220/145152 [01:13<00:00, 2805.56 examples/s][A
+Generating train split: 100%|██████████| 145152/145152 [01:13<00:00, 1966.96 examples/s]
 Generating validation split:   0%|          | 0/239 [00:00<?, ? examples/s][A
+Generating validation split: 100%|██████████| 239/239 [00:00<00:00, 280.49 examples/s]
 Generating test split:   0%|          | 0/418 [00:00<?, ? examples/s][A
+Generating test split:  48%|████▊     | 200/418 [00:01<00:01, 163.89 examples/s][A
+Generating test split: 100%|██████████| 418/418 [00:01<00:00, 253.17 examples/s]
+02/07/2026 06:40:01 - INFO - __main__ - *** Training T3 model ***
+  0%|          | 0/145152 [00:00<?, ?it/s][A02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 16: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 40: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 8: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 32: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 0: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 48: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 56: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 24: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 33: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 57: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 1: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 49: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 17: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 34: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 35: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 58: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 50: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 25: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 36: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 18: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 51: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 37: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 26: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 59: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 2: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 19: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 52: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 60: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 3: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 38: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 20: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 27: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 53: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 39: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - WARNING - __main__ - SpeechDataCollator received no valid features. Returning empty batch.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 21: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 54: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 61: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 28: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 22: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 55: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - WARNING - __main__ - SpeechDataCollator received no valid features. Returning empty batch.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 29: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 62: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 63: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 30: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - WARNING - __main__ - SpeechDataCollator received no valid features. Returning empty batch.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 23: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - WARNING - __main__ - SpeechDataCollator received no valid features. Returning empty batch.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 4: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 41: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 9: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 31: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - WARNING - __main__ - SpeechDataCollator received no valid features. Returning empty batch.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 5: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 96: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 80: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 42: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 10: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 97: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 120: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 6: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 43: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 11: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 81: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 88: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 121: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 44: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 7: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 12: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - WARNING - __main__ - SpeechDataCollator received no valid features. Returning empty batch.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 122: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 89: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 45: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 90: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 82: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 98: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 64: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 123: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 91: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 99: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 46: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 83: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 124: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 13: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 92: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 65: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 47: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 125: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 100: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - WARNING - __main__ - SpeechDataCollator received no valid features. Returning empty batch.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 84: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 14: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 126: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 66: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 85: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 15: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 112: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 104: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - WARNING - __main__ - SpeechDataCollator received no valid features. Returning empty batch.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 67: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 127: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - WARNING - __main__ - SpeechDataCollator received no valid features. Returning empty batch.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 86: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 101: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 113: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 105: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 68: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 87: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - WARNING - __main__ - SpeechDataCollator received no valid features. Returning empty batch.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 72: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 102: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 93: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 114: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 106: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 69: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 73: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 115: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 94: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 103: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - WARNING - __main__ - SpeechDataCollator received no valid features. Returning empty batch.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 107: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 70: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 95: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 116: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 108: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - WARNING - __main__ - SpeechDataCollator received no valid features. Returning empty batch.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 71: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - WARNING - __main__ - SpeechDataCollator received no valid features. Returning empty batch.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 117: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 109: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 118: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 110: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 74: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 119: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - WARNING - __main__ - SpeechDataCollator received no valid features. Returning empty batch.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 111: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - WARNING - __main__ - SpeechDataCollator received no valid features. Returning empty batch.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 75: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 76: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 77: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 78: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - ERROR - __main__ - Unexpected audio data format for item 79: <class 'datasets.features._torchcodec.AudioDecoder'>. Skipping.
+02/07/2026 06:40:04 - WARNING - __main__ - SpeechDataCollator received no valid features. Returning empty batch.
 Traceback (most recent call last):
+  File "/app/chatterbox-multilingual-finetuning/src/finetune_t3.py", line 790, in <module>
     main()
     ~~~~^^
+  File "/app/chatterbox-multilingual-finetuning/src/finetune_t3.py", line 737, 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 4478, in evaluation_loop
+    losses, logits, labels = self.prediction_step(model, inputs, prediction_loss_only, ignore_keys=ignore_keys)
+                             ~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/usr/local/lib/python3.13/site-packages/transformers/trainer.py", line 4649, in prediction_step
+    inputs = self._prepare_inputs(inputs)
+  File "/usr/local/lib/python3.13/site-packages/transformers/trainer.py", line 3610, in _prepare_inputs
+    raise ValueError(
+    ...<2 lines>...
+    )
+ValueError: The batch received was empty, your model won't be able to train on it. Double-check that your training dataset contains keys expected by the model: text_tokens,text_token_lens,speech_tokens,speech_token_lens,t3_cond_speaker_emb,t3_cond_prompt_speech_tokens,t3_cond_emotion_adv,labels_text,labels_speech,label,labels_speech,label_ids.
+  0%|          | 0/145152 [00:04<?, ?it/s]