End of training

README.md

@@ -16,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model was trained from scratch on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: nan
-- Cer: 1.0
-- Wer: 1.0
+- Loss: 2.0007
+- Cer: 0.3962
+- Wer: 0.6069
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 5.6,
+    "eval_cer": 0.39621716426834613,
+    "eval_loss": 2.00065016746521,
+    "eval_runtime": 157.5611,
+    "eval_samples": 3136,
+    "eval_samples_per_second": 19.903,
+    "eval_steps_per_second": 1.244,
+    "eval_wer": 0.6068801160501502,
+    "total_flos": 2.158464150901847e+19,
+    "train_loss": 1.3790143143790108,
+    "train_runtime": 12492.843,
+    "train_samples": 20000,
+    "train_samples_per_second": 8.965,
+    "train_steps_per_second": 0.28
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 5.6,
+    "eval_cer": 0.39621716426834613,
+    "eval_loss": 2.00065016746521,
+    "eval_runtime": 157.5611,
+    "eval_samples": 3136,
+    "eval_samples_per_second": 19.903,
+    "eval_steps_per_second": 1.244,
+    "eval_wer": 0.6068801160501502
+}

indicwav2vec_trainwtags_MUCS_warmup1500_s300shuff100_2212167.out

@@ -12342,3 +12342,127 @@ last prediction string
 
                                                 
 
 
                                                 
                                                     
+Printing predictions for a few samples:
+Sample 1:
+  Reference: लिबर ऑफिस <cs> impress </cs> में एक प्रस्तुति <cs> document </cs> बनाना और बुनियादी <cs> formatting </cs> के इस <cs> spoken  tutorial </cs> में आपका स्वागत है
+######
+
+
+  Prediction: 
+
+
+
+Sample 2:
+  Reference: इस <cs> tutorial </cs> में हम <cs> impress  window </cs> के भागों के बारे में सीखेंगे और कैसे स्लाइड इन्सर्ट करें और कॉपी करें फॉन्ट तथा फॉन्ट को फॉर्मेट करना सीखेंगे
+######
+
+
+  Prediction: 
+
+
+
+Sample 3:
+  Reference: यहाँ हम अपने ऑपरेटिंग सिस्टम के रूप में gnu/linux और लिबरऑफिस वर्जन <cs> 334 </cs> का उपयोग कर रहे हैं
+######
+
+
+  Prediction: 
+
+
+
+Sample 4:
+  Reference: चलिए अपनी प्रस्तुति प्रेजैटेशन <cs> sample  impress  open </cs> करते हैं जिसे पिछले <cs> tutorial </cs> में बनाया था
+######
+
+
+  Prediction: 
+
+
+
+Sample 5:
+  Reference: चलिए देखते हैं कि <cs> screen </cs> पर क्या क्या है
+######
+
+
+  Prediction: 
+
+
+
+last Reference string यह स्क्रिप्ट लता द्वारा अनुवादित है आईआईटी मुंबई की ओर से मैं रवि कुमार अब आपसे विदा लेता हूँहमसे जुड़ने के लिए धन्यवाद
+
+
+last prediction string 
+{'eval_loss': nan, 'eval_cer': 1.0, 'eval_wer': 1.0, 'eval_runtime': 157.361, 'eval_samples_per_second': 19.929, 'eval_steps_per_second': 1.246, 'epoch': 5.6}
+{'train_runtime': 12492.843, 'train_samples_per_second': 8.965, 'train_steps_per_second': 0.28, 'train_loss': 1.3790143143790108, 'epoch': 5.6}
+***** train metrics *****
+  epoch                    =           5.6
+  total_flos               = 20102263902GF
+  train_loss               =         1.379
+  train_runtime            =    3:28:12.84
+  train_samples            =         20000
+  train_samples_per_second =         8.965
+  train_steps_per_second   =          0.28
+08/28/2024 05:57:30 - INFO - __main__ - *** Evaluate ***
+/scratch/work/palp3/myenv/lib/python3.11/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.
+  warnings.warn(
+
  0%|          | 0/196 [00:00<?, ?it/s]
  1%|          | 2/196 [00:00<01:01,  3.14it/s]
  2%|▏         | 3/196 [00:01<01:29,  2.16it/s]
  2%|▏         | 4/196 [00:02<01:50,  1.73it/s]
  3%|▎         | 5/196 [00:02<02:03,  1.54it/s]
  3%|▎         | 6/196 [00:03<02:20,  1.35it/s]
  4%|▎         | 7/196 [00:04<02:23,  1.31it/s]
  4%|▍         | 8/196 [00:05<02:32,  1.23it/s]
  5%|▍         | 9/196 [00:07<03:20,  1.07s/it]
  5%|▌         | 10/196 [00:08<03:53,  1.25s/it]
  6%|▌         | 11/196 [00:10<04:27,  1.44s/it]
  6%|▌         | 12/196 [00:12<04:33,  1.49s/it]
  7%|▋         | 13/196 [00:13<03:57,  1.30s/it]
  7%|▋         | 14/196 [00:13<03:21,  1.11s/it]
  8%|▊         | 15/196 [00:14<02:52,  1.05it/s]
  8%|▊         | 16/196 [00:15<02:41,  1.11it/s]
  9%|▊         | 17/196 [00:16<02:40,  1.12it/s]
  9%|▉         | 18/196 [00:17<03:01,  1.02s/it]
 10%|▉         | 19/196 [00:19<03:48,  1.29s/it]
 10%|█         | 20/196 [00:20<03:58,  1.36s/it]
 11%|█         | 21/196 [00:22<04:05,  1.41s/it]
 11%|█         | 22/196 [00:23<03:50,  1.32s/it]
 12%|█▏        | 23/196 [00:24<03:25,  1.19s/it]
 12%|█▏        | 24/196 [00:24<02:46,  1.03it/s]
 13%|█▎        | 25/196 [00:25<02:25,  1.18it/s]
 13%|█▎        | 26/196 [00:25<02:08,  1.32it/s]
 14%|█▍        | 27/196 [00:26<02:02,  1.38it/s]
 14%|█▍        | 28/196 [00:27<01:57,  1.44it/s]
 15%|█▍        | 29/196 [00:27<01:57,  1.42it/s]
 15%|█▌        | 30/196 [00:28<01:55,  1.44it/s]
 16%|█▌        | 31/196 [00:29<01:44,  1.59it/s]
 16%|█▋        | 32/196 [00:29<01:44,  1.57it/s]
 17%|█▋        | 33/196 [00:30<01:59,  1.37it/s]
 17%|█▋        | 34/196 [00:31<02:24,  1.12it/s]
 18%|█▊        | 35/196 [00:33<02:35,  1.04it/s]
 18%|█▊        | 36/196 [00:34<02:51,  1.07s/it]
 19%|█▉        | 37/196 [00:35<02:44,  1.04s/it]
 19%|█▉        | 38/196 [00:36<02:33,  1.03it/s]
 20%|█▉        | 39/196 [00:36<02:22,  1.11it/s]
 20%|██        | 40/196 [00:37<02:12,  1.17it/s]
 21%|██        | 41/196 [00:38<02:01,  1.27it/s]
 21%|██▏       | 42/196 [00:38<01:57,  1.31it/s]
 22%|██▏       | 43/196 [00:39<01:54,  1.34it/s]
 22%|██▏       | 44/196 [00:40<01:50,  1.38it/s]
 23%|██▎       | 45/196 [00:40<01:42,  1.48it/s]
 23%|██▎       | 46/196 [00:41<01:37,  1.54it/s]
 24%|██▍       | 47/196 [00:42<01:36,  1.54it/s]
 24%|██▍       | 48/196 [00:42<01:34,  1.56it/s]
 25%|██▌       | 49/196 [00:43<01:33,  1.58it/s]
 26%|██▌       | 50/196 [00:44<01:31,  1.60it/s]
 26%|██▌       | 51/196 [00:44<01:28,  1.63it/s]
 27%|██▋       | 52/196 [00:45<01:30,  1.60it/s]
 27%|██▋       | 53/196 [00:45<01:30,  1.58it/s]
 28%|██▊       | 54/196 [00:46<01:30,  1.57it/s]
 28%|██▊       | 55/196 [00:47<01:38,  1.43it/s]
 29%|██▊       | 56/196 [00:48<01:45,  1.32it/s]
 29%|██▉       | 57/196 [00:49<01:50,  1.25it/s]
 30%|██▉       | 58/196 [00:50<01:52,  1.23it/s]
 30%|███       | 59/196 [00:50<01:49,  1.25it/s]
 31%|███       | 60/196 [00:51<01:38,  1.39it/s]
 31%|███       | 61/196 [00:51<01:32,  1.46it/s]
 32%|███▏      | 62/196 [00:52<01:33,  1.44it/s]
 32%|███▏      | 63/196 [00:53<01:34,  1.41it/s]
 33%|███▎      | 64/196 [00:54<01:33,  1.41it/s]
 33%|███▎      | 65/196 [00:54<01:32,  1.42it/s]
 34%|███▎      | 66/196 [00:55<01:37,  1.34it/s]
 34%|███▍      | 67/196 [00:56<01:39,  1.29it/s]
 35%|███▍      | 68/196 [00:57<01:50,  1.16it/s]
 35%|███▌      | 69/196 [00:58<01:48,  1.17it/s]
 36%|███▌      | 70/196 [00:59<01:41,  1.24it/s]
 36%|███▌      | 71/196 [00:59<01:35,  1.31it/s]
 37%|███▋      | 72/196 [01:00<01:29,  1.39it/s]
 37%|███▋      | 73/196 [01:00<01:22,  1.50it/s]
 38%|███▊      | 74/196 [01:01<01:18,  1.56it/s]
 38%|███▊      | 75/196 [01:02<01:16,  1.59it/s]
 39%|███▉      | 76/196 [01:02<01:14,  1.62it/s]
 39%|███▉      | 77/196 [01:03<01:17,  1.53it/s]
 40%|███▉      | 78/196 [01:04<01:18,  1.50it/s]
 40%|████      | 79/196 [01:04<01:16,  1.52it/s]
 41%|████      | 80/196 [01:05<01:21,  1.43it/s]
 41%|████▏     | 81/196 [01:06<01:21,  1.41it/s]
 42%|████▏     | 82/196 [01:06<01:19,  1.43it/s]
 42%|████▏     | 83/196 [01:07<01:21,  1.38it/s]
 43%|████▎     | 84/196 [01:08<01:21,  1.37it/s]
 43%|████▎     | 85/196 [01:09<01:21,  1.37it/s]
 44%|████▍     | 86/196 [01:10<01:22,  1.33it/s]
 44%|████▍     | 87/196 [01:10<01:21,  1.34it/s]
 45%|████▍     | 88/196 [01:11<01:22,  1.31it/s]
 45%|████▌     | 89/196 [01:12<01:23,  1.27it/s]
 46%|████▌     | 90/196 [01:13<01:22,  1.29it/s]
 46%|████▋     | 91/196 [01:13<01:17,  1.36it/s]
 47%|████▋     | 92/196 [01:14<01:14,  1.40it/s]
 47%|████▋     | 93/196 [01:15<01:17,  1.32it/s]
 48%|████▊     | 94/196 [01:16<01:16,  1.34it/s]
 48%|████▊     | 95/196 [01:16<01:14,  1.35it/s]
 49%|████▉     | 96/196 [01:17<01:17,  1.29it/s]
 49%|████▉     | 97/196 [01:18<01:13,  1.34it/s]
 50%|█████     | 98/196 [01:19<01:14,  1.31it/s]
 51%|█████     | 99/196 [01:19<01:08,  1.41it/s]
 51%|█████     | 100/196 [01:20<01:00,  1.59it/s]
 52%|█████▏    | 101/196 [01:20<00:59,  1.60it/s]
 52%|█████▏    | 102/196 [01:21<01:02,  1.50it/s]
 53%|█████▎    | 103/196 [01:22<01:08,  1.36it/s]
 53%|█████▎    | 104/196 [01:23<01:15,  1.22it/s]
 54%|█████▎    | 105/196 [01:24<01:15,  1.20it/s]
 54%|█████▍    | 106/196 [01:25<01:13,  1.22it/s]
 55%|█████▍    | 107/196 [01:25<01:08,  1.30it/s]
 55%|█████▌    | 108/196 [01:26<01:00,  1.45it/s]
 56%|█████▌    | 109/196 [01:26<00:58,  1.48it/s]
 56%|█████▌    | 110/196 [01:27<00:57,  1.50it/s]
 57%|█████▋    | 111/196 [01:28<00:57,  1.49it/s]
 57%|█████▋    | 112/196 [01:28<00:58,  1.44it/s]
 58%|█████▊    | 113/196 [01:29<00:57,  1.45it/s]
 58%|█████▊    | 114/196 [01:30<00:52,  1.55it/s]
 59%|█████▊    | 115/196 [01:30<00:51,  1.58it/s]
 59%|█████▉    | 116/196 [01:31<00:50,  1.59it/s]
 60%|█████▉    | 117/196 [01:31<00:46,  1.70it/s]
 60%|██████    | 118/196 [01:32<00:41,  1.86it/s]
 61%|██████    | 119/196 [01:32<00:44,  1.72it/s]
 61%|██████    | 120/196 [01:33<00:45,  1.66it/s]
 62%|██████▏   | 121/196 [01:34<00:46,  1.62it/s]
 62%|██████▏   | 122/196 [01:34<00:46,  1.58it/s]
 63%|██████▎   | 123/196 [01:35<00:45,  1.62it/s]
 63%|██████▎   | 124/196 [01:36<00:45,  1.58it/s]
 64%|██████▍   | 125/196 [01:36<00:45,  1.56it/s]
 64%|██████▍   | 126/196 [01:37<00:51,  1.37it/s]
 65%|██████▍   | 127/196 [01:38<00:48,  1.41it/s]
 65%|██████▌   | 128/196 [01:39<00:46,  1.46it/s]
 66%|██████▌   | 129/196 [01:39<00:45,  1.48it/s]
 66%|██████▋   | 130/196 [01:40<00:45,  1.46it/s]
 67%|██████▋   | 131/196 [01:41<00:43,  1.49it/s]
 67%|██████▋   | 132/196 [01:41<00:40,  1.58it/s]
 68%|██████▊   | 133/196 [01:42<00:39,  1.58it/s]
 68%|██████▊   | 134/196 [01:42<00:40,  1.53it/s]
 69%|██████▉   | 135/196 [01:43<00:39,  1.56it/s]
 69%|██████▉   | 136/196 [01:44<00:38,  1.56it/s]
 70%|██████▉   | 137/196 [01:44<00:37,  1.56it/s]
 70%|███████   | 138/196 [01:45<00:36,  1.57it/s]
 71%|███████   | 139/196 [01:46<00:37,  1.53it/s]
 71%|███████▏  | 140/196 [01:46<00:35,  1.58it/s]
 72%|███████▏  | 141/196 [01:47<00:34,  1.61it/s]
 72%|███████▏  | 142/196 [01:48<00:34,  1.56it/s]
 73%|███████▎  | 143/196 [01:48<00:35,  1.50it/s]
 73%|███████▎  | 144/196 [01:49<00:33,  1.56it/s]
 74%|███████▍  | 145/196 [01:49<00:30,  1.68it/s]
 74%|███████▍  | 146/196 [01:50<00:28,  1.74it/s]
 75%|███████▌  | 147/196 [01:50<00:28,  1.74it/s]
 76%|███████▌  | 148/196 [01:51<00:27,  1.72it/s]
 76%|███████▌  | 149/196 [01:52<00:25,  1.81it/s]
 77%|███████▋  | 150/196 [01:52<00:27,  1.66it/s]
 77%|███████▋  | 151/196 [01:53<00:28,  1.60it/s]
 78%|███████▊  | 152/196 [01:54<00:27,  1.60it/s]
 78%|███████▊  | 153/196 [01:54<00:27,  1.59it/s]
 79%|███████▊  | 154/196 [01:55<00:26,  1.59it/s]
 79%|███████▉  | 155/196 [01:56<00:27,  1.48it/s]
 80%|███████▉  | 156/196 [01:56<00:29,  1.34it/s]
 80%|████████  | 157/196 [01:57<00:30,  1.29it/s]
 81%|████████  | 158/196 [01:58<00:26,  1.43it/s]
 81%|████████  | 159/196 [01:58<00:24,  1.53it/s]
 82%|████████▏ | 160/196 [01:59<00:23,  1.56it/s]
 82%|████████▏ | 161/196 [02:00<00:22,  1.54it/s]
 83%|████████▎ | 162/196 [02:00<00:21,  1.56it/s]
 83%|████████▎ | 163/196 [02:01<00:20,  1.58it/s]
 84%|████████▎ | 164/196 [02:02<00:20,  1.58it/s]
 84%|████████▍ | 165/196 [02:02<00:20,  1.53it/s]
 85%|████████▍ | 166/196 [02:03<00:19,  1.57it/s]
 85%|████████▌ | 167/196 [02:03<00:18,  1.60it/s]
 86%|████████▌ | 168/196 [02:04<00:16,  1.69it/s]
 86%|████████▌ | 169/196 [02:05<00:16,  1.60it/s]
 87%|████████▋ | 170/196 [02:05<00:17,  1.51it/s]
 87%|████████▋ | 171/196 [02:06<00:16,  1.53it/s]
 88%|████████▊ | 172/196 [02:07<00:16,  1.50it/s]
 88%|████████▊ | 173/196 [02:07<00:15,  1.50it/s]
 89%|████████▉ | 174/196 [02:08<00:15,  1.42it/s]
 89%|████████▉ | 175/196 [02:09<00:18,  1.15it/s]
 90%|████████▉ | 176/196 [02:12<00:25,  1.26s/it]
 90%|█████████ | 177/196 [02:13<00:27,  1.43s/it]
 91%|█████████ | 178/196 [02:15<00:28,  1.61s/it]
 91%|█████████▏| 179/196 [02:17<00:27,  1.62s/it]
 92%|█████████▏| 180/196 [02:18<00:21,  1.33s/it]
 92%|█████████▏| 181/196 [02:18<00:16,  1.13s/it]
 93%|█████████▎| 182/196 [02:19<00:13,  1.01it/s]
 93%|█████████▎| 183/196 [02:20<00:12,  1.03it/s]
 94%|█████████▍| 184/196 [02:21<00:10,  1.14it/s]
 94%|█████████▍| 185/196 [02:21<00:09,  1.18it/s]
 95%|█████████▍| 186/196 [02:22<00:08,  1.17it/s]
 95%|█████████▌| 187/196 [02:23<00:07,  1.27it/s]
 96%|█████████▌| 188/196 [02:24<00:05,  1.35it/s]
 96%|█████████▋| 189/196 [02:24<00:05,  1.38it/s]
 97%|█████████▋| 190/196 [02:25<00:04,  1.45it/s]
 97%|█████████▋| 191/196 [02:25<00:03,  1.53it/s]
 98%|█████████▊| 192/196 [02:26<00:02,  1.50it/s]
 98%|█████████▊| 193/196 [02:27<00:02,  1.46it/s]
 99%|█████████▉| 194/196 [02:28<00:01,  1.49it/s]
 99%|█████████▉| 195/196 [02:28<00:00,  1.54it/s]
+Printing predictions for a few samples:
+Sample 1:
+  Reference: लिबर ऑफिस <cs> impress </cs> में एक प्रस्तुति <cs> document </cs> बनाना और बुनियादी <cs> formatting </cs> के इस <cs> spoken  tutorial </cs> में आपका स्वागत है
+######
+
+
+  Prediction: cs> iber  oफis s> imps </cs> में एक प्रसतुति <cs> documet /cs> बनाना और बुनियादी <cs> formatin </cs> के इस <css poken > tutoral<cs> में आपक ा
+
+
+
+Sample 2:
+  Reference: इस <cs> tutorial </cs> में हम <cs> impress  window </cs> के भागों के बारे में सीखेंगे और कैसे स्लाइड इन्सर्ट करें और कॉपी करें फॉन्ट तथा फॉन्ट को फॉर्मेट करना सीखेंगे
+######
+
+
+  Prediction: इस <cs> tutorial </cs> में हम <cs> impres <> winडo </cs> के भागों के बारे में सीखेंगे और कैसे <cs> slide  insert </cs> करें और <cs> cop </cs> करेंcs> font </cs> तथा <cs> font </cs> को <cs> format </cs> करना सीखेंगे
+
+
+
+Sample 3:
+  Reference: यहाँ हम अपने ऑपरेटिंग सिस्टम के रूप में gnu/linux और लिबरऑफिस वर्जन <cs> 334 </cs> का उपयोग कर रहे हैं
+######
+
+
+  Prediction: यहाँ हम अपने <cs> oprain  sistem /cs> के रूप में <cs> gnu < linux </cs>और <cs> liber  ofis > verion <css> </cs> का उपयोग कर रहेैं
+
+
+
+Sample 4:
+  Reference: चलिए अपनी प्रस्तुति प्रेजैटेशन <cs> sample  impress  open </cs> करते हैं जिसे पिछले <cs> tutorial </cs> में बनाया था
+######
+
+
+  Prediction: चलिए अपनी प्रस्तुति <ccs> sampl > imps > open </cs> करते हैं जिसे पिछ <c
+
+
+
+Sample 5:
+  Reference: चलिए देखते हैं कि <cs> screen </cs> पर क्या क्या है
+######
+
+
+  Prediction: चलिए देखते हैं कि <cs> scren </cs> पर क्या क्या है
+
+
+
+last Reference string यह स्क्रिप्ट लता द्वारा अनुवादित है आईआईटी मुंबई की ओर से मैं रवि कुमार अब आपसे विदा लेता हूँहमसे जुड़ने के लिए धन्यवाद
+
+
+last prediction string cs> लत/s> द्वरा अनुवादित है आईआईटी मुंबई की ओर से मैं रवि कुमार अब आपसे विदा लेता हूँहमसे जुड़ने के लिए धन्यवाद
+***** eval metrics *****
+  epoch                   =        5.6
+  eval_cer                =     0.3962
+  eval_loss               =     2.0007
+  eval_runtime            = 0:02:37.56
+  eval_samples            =       3136
+  eval_samples_per_second =     19.903
+  eval_steps_per_second   =      1.244
+  eval_wer                =     0.6069
+

predictionswtags_indicw2v_ad0_3_hd_02_featd_0_2_lr6e-4_warmup1500_s300_shuff100.txt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f89aa4e0899f60cc0c21562c4359607bc1361426e9cd8afc89564a2c0f81e02
-size 23060883
+oid sha256:f6c01a489567285af2c593b021150526769cd8fc6436fbec716d2be55370ac92
+size 23608120

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.6,
+    "total_flos": 2.158464150901847e+19,
+    "train_loss": 1.3790143143790108,
+    "train_runtime": 12492.843,
+    "train_samples": 20000,
+    "train_samples_per_second": 8.965,
+    "train_steps_per_second": 0.28
+}