End of training

README.md

@@ -1,8 +1,6 @@
 ---
 tags:
 - generated_from_trainer
-metrics:
-- wer
 model-index:
 - name: s300_shuff100
   results: []
@@ -11,14 +9,19 @@ model-index:
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/priyanshipal/huggingface/runs/0evkescz)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/priyanshipal/huggingface/runs/jw39kyll)
 # s300_shuff100
 
 This model was trained from scratch on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.5066
-- Cer: 0.3096
-- Wer: 0.4357
+- eval_loss: nan
+- eval_model_preparation_time: 0.0044
+- eval_cer: 1.0
+- eval_wer: 1.0
+- eval_runtime: 40.6214
+- eval_samples_per_second: 14.081
+- eval_steps_per_second: 0.886
+- step: 0
 
 ## Model description
 
@@ -49,13 +52,6 @@ The following hyperparameters were used during training:
 - training_steps: 1000
 - mixed_precision_training: Native AMP
 
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss | Cer    | Wer    |
-|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
-| 0.9856        | 1.6   | 1000 | 1.5066          | 0.3096 | 0.4357 |
-
-
 ### Framework versions
 
 - Transformers 4.43.1

all_results.json

@@ -1,12 +1,13 @@
 {
     "epoch": 1.6,
-    "eval_cer": 0.30955352407101183,
-    "eval_loss": 1.5066314935684204,
-    "eval_runtime": 159.3193,
-    "eval_samples": 3136,
-    "eval_samples_per_second": 19.684,
-    "eval_steps_per_second": 1.23,
-    "eval_wer": 0.43571675485946765,
+    "eval_cer": 1.0,
+    "eval_loss": NaN,
+    "eval_model_preparation_time": 0.0044,
+    "eval_runtime": 40.6214,
+    "eval_samples": 572,
+    "eval_samples_per_second": 14.081,
+    "eval_steps_per_second": 0.886,
+    "eval_wer": 1.0,
     "total_flos": 6.212261523683712e+18,
     "train_loss": 3.21392811447382,
     "train_runtime": 2133.1271,

config.json

@@ -9,7 +9,7 @@
   "architectures": [
     "Wav2Vec2ForCTC"
   ],
-  "attention_dropout": 0.3,
+  "attention_dropout": 0.0,
   "bos_token_id": 1,
   "classifier_proj_size": 256,
   "codevector_dim": 256,
@@ -50,11 +50,11 @@
   "feat_extract_activation": "gelu",
   "feat_extract_dropout": 0.0,
   "feat_extract_norm": "layer",
-  "feat_proj_dropout": 0.3,
+  "feat_proj_dropout": 0.0,
   "feat_quantizer_dropout": 0.0,
   "final_dropout": 0.0,
   "hidden_act": "gelu",
-  "hidden_dropout": 0.2,
+  "hidden_dropout": 0.0,
   "hidden_dropout_prob": 0.1,
   "hidden_size": 1024,
   "initializer_range": 0.02,

eval_results.json

@@ -1,10 +1,10 @@
 {
-    "epoch": 1.6,
-    "eval_cer": 0.30955352407101183,
-    "eval_loss": 1.5066314935684204,
-    "eval_runtime": 159.3193,
-    "eval_samples": 3136,
-    "eval_samples_per_second": 19.684,
-    "eval_steps_per_second": 1.23,
-    "eval_wer": 0.43571675485946765
+    "eval_cer": 1.0,
+    "eval_loss": NaN,
+    "eval_model_preparation_time": 0.0044,
+    "eval_runtime": 40.6214,
+    "eval_samples": 572,
+    "eval_samples_per_second": 14.081,
+    "eval_steps_per_second": 0.886,
+    "eval_wer": 1.0
 }

evalonly_indicwav2vec_MUCS_warmup500_s300shuff100_2142198.out

@@ -0,0 +1,44 @@
+wandb: Currently logged in as: priyanshi-pal (priyanshipal). Use `wandb login --relogin` to force relogin
+wandb: wandb version 0.17.7 is available!  To upgrade, please run:
+wandb:  $ pip install wandb --upgrade
+wandb: Tracking run with wandb version 0.17.6
+wandb: Run data is saved locally in /scratch/elec/t405-puhe/p/palp3/MUCS/wandb/run-20240822_143902-r64ufk4q
+wandb: Run `wandb offline` to turn off syncing.
+wandb: Syncing run eval_pd2000_s300_shuff100_hindi
+wandb: ⭐️ View project at https://wandb.ai/priyanshipal/huggingface
+wandb: 🚀 View run at https://wandb.ai/priyanshipal/huggingface/runs/r64ufk4q
+/scratch/work/palp3/myenv/lib/python3.11/site-packages/transformers/training_args.py:1525: FutureWarning: `evaluation_strategy` is deprecated and will be removed in version 4.46 of 🤗 Transformers. Use `eval_strategy` instead
+  warnings.warn(
+
+Traceback (most recent call last):
+  File "/scratch/work/palp3/myenv/lib/python3.11/site-packages/datasets/builder.py", line 1997, in _prepare_split_single
+    for _, table in generator:
+  File "/scratch/work/palp3/myenv/lib/python3.11/site-packages/datasets/packaged_modules/json/json.py", line 98, in _generate_tables
+    dataset = dataset[self.config.field]
+              ~~~~~~~^^^^^^^^^^^^^^^^^^^
+KeyError: 'test'
+
+The above exception was the direct cause of the following exception:
+
+Traceback (most recent call last):
+  File "/scratch/elec/puhe/p/palp3/MUCS/eval_script_indicwav2vec.py", line 790, in <module>
+    main()
+  File "/scratch/elec/puhe/p/palp3/MUCS/eval_script_indicwav2vec.py", line 427, in main
+    raw_datasets["eval"] = load_dataset(
+                           ^^^^^^^^^^^^^
+  File "/scratch/work/palp3/myenv/lib/python3.11/site-packages/datasets/load.py", line 2616, in load_dataset
+    builder_instance.download_and_prepare(
+  File "/scratch/work/palp3/myenv/lib/python3.11/site-packages/datasets/builder.py", line 1029, in download_and_prepare
+    self._download_and_prepare(
+  File "/scratch/work/palp3/myenv/lib/python3.11/site-packages/datasets/builder.py", line 1124, in _download_and_prepare
+    self._prepare_split(split_generator, **prepare_split_kwargs)
+  File "/scratch/work/palp3/myenv/lib/python3.11/site-packages/datasets/builder.py", line 1884, in _prepare_split
+    for job_id, done, content in self._prepare_split_single(
+  File "/scratch/work/palp3/myenv/lib/python3.11/site-packages/datasets/builder.py", line 2040, in _prepare_split_single
+    raise DatasetGenerationError("An error occurred while generating the dataset") from e
+datasets.exceptions.DatasetGenerationError: An error occurred while generating the dataset
+wandb: - 0.005 MB of 0.005 MB uploaded
+wandb: ⭐️ View project at: https://wandb.ai/priyanshipal/huggingface
+wandb: Synced 6 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)
+wandb: Find logs at: ./wandb/run-20240822_143902-r64ufk4q/logs
+wandb: WARNING The new W&B backend becomes opt-out in version 0.18.0; try it out with `wandb.require("core")`! See https://wandb.me/wandb-core for more information.

evalonlyhindi_indicwav2vec_MUCS_warmup500_s300shuff100_2142336.out

@@ -0,0 +1,463 @@
+wandb: Currently logged in as: priyanshi-pal (priyanshipal). Use `wandb login --relogin` to force relogin
+wandb: wandb version 0.17.7 is available!  To upgrade, please run:
+wandb:  $ pip install wandb --upgrade
+wandb: Tracking run with wandb version 0.17.6
+wandb: Run data is saved locally in /scratch/elec/t405-puhe/p/palp3/MUCS/wandb/run-20240822_145052-jw39kyll
+wandb: Run `wandb offline` to turn off syncing.
+wandb: Syncing run eval_pd2000_s300_shuff100_hindi
+wandb: ⭐️ View project at https://wandb.ai/priyanshipal/huggingface
+wandb: 🚀 View run at https://wandb.ai/priyanshipal/huggingface/runs/jw39kyll
+/scratch/work/palp3/myenv/lib/python3.11/site-packages/transformers/training_args.py:1525: FutureWarning: `evaluation_strategy` is deprecated and will be removed in version 4.46 of 🤗 Transformers. Use `eval_strategy` instead
+  warnings.warn(
+
+/scratch/work/palp3/myenv/lib/python3.11/site-packages/transformers/models/auto/configuration_auto.py:957: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
+  warnings.warn(
+/scratch/work/palp3/myenv/lib/python3.11/site-packages/transformers/configuration_utils.py:364: UserWarning: Passing `gradient_checkpointing` to a config initialization is deprecated and will be removed in v5 Transformers. Using `model.gradient_checkpointing_enable()` instead, or if you are using the `Trainer` API, pass `gradient_checkpointing=True` in your `TrainingArguments`.
+  warnings.warn(
+/scratch/work/palp3/myenv/lib/python3.11/site-packages/transformers/models/auto/feature_extraction_auto.py:329: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
+  warnings.warn(
+Wav2Vec2CTCTokenizer(name_or_path='', vocab_size=149, model_max_length=1000000000000000019884624838656, is_fast=False, padding_side='right', truncation_side='right', special_tokens={'bos_token': '<s>', 'eos_token': '</s>', 'unk_token': '[UNK]', 'pad_token': '[PAD]'}, clean_up_tokenization_spaces=True),  added_tokens_decoder={
+	147: AddedToken("[UNK]", rstrip=True, lstrip=True, single_word=False, normalized=False, special=False),
+	148: AddedToken("[PAD]", rstrip=True, lstrip=True, single_word=False, normalized=False, special=False),
+	149: AddedToken("<s>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+	150: AddedToken("</s>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+}
+CHECK MODEL PARAMS Wav2Vec2ForCTC(
+  (wav2vec2): Wav2Vec2Model(
+    (feature_extractor): Wav2Vec2FeatureEncoder(
+      (conv_layers): ModuleList(
+        (0): Wav2Vec2LayerNormConvLayer(
+          (conv): Conv1d(1, 512, kernel_size=(10,), stride=(5,))
+          (layer_norm): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
+          (activation): GELUActivation()
+        )
+        (1-4): 4 x Wav2Vec2LayerNormConvLayer(
+          (conv): Conv1d(512, 512, kernel_size=(3,), stride=(2,))
+          (layer_norm): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
+          (activation): GELUActivation()
+        )
+        (5-6): 2 x Wav2Vec2LayerNormConvLayer(
+          (conv): Conv1d(512, 512, kernel_size=(2,), stride=(2,))
+          (layer_norm): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
+          (activation): GELUActivation()
+        )
+      )
+    )
+    (feature_projection): Wav2Vec2FeatureProjection(
+      (layer_norm): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
+      (projection): Linear(in_features=512, out_features=1024, bias=True)
+      (dropout): Dropout(p=0.0, inplace=False)
+    )
+    (encoder): Wav2Vec2EncoderStableLayerNorm(
+      (pos_conv_embed): Wav2Vec2PositionalConvEmbedding(
+        (conv): ParametrizedConv1d(
+          1024, 1024, kernel_size=(128,), stride=(1,), padding=(64,), groups=16
+          (parametrizations): ModuleDict(
+            (weight): ParametrizationList(
+              (0): _WeightNorm()
+            )
+          )
+        )
+        (padding): Wav2Vec2SamePadLayer()
+        (activation): GELUActivation()
+      )
+      (layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
+      (dropout): Dropout(p=0.0, inplace=False)
+      (layers): ModuleList(
+        (0-23): 24 x Wav2Vec2EncoderLayerStableLayerNorm(
+          (attention): Wav2Vec2SdpaAttention(
+            (k_proj): Linear(in_features=1024, out_features=1024, bias=True)
+            (v_proj): Linear(in_features=1024, out_features=1024, bias=True)
+            (q_proj): Linear(in_features=1024, out_features=1024, bias=True)
+            (out_proj): Linear(in_features=1024, out_features=1024, bias=True)
+          )
+          (dropout): Dropout(p=0.0, inplace=False)
+          (layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
+          (feed_forward): Wav2Vec2FeedForward(
+            (intermediate_dropout): Dropout(p=0.0, inplace=False)
+            (intermediate_dense): Linear(in_features=1024, out_features=4096, bias=True)
+            (intermediate_act_fn): GELUActivation()
+            (output_dense): Linear(in_features=4096, out_features=1024, bias=True)
+            (output_dropout): Dropout(p=0.0, inplace=False)
+          )
+          (final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
+        )
+      )
+    )
+  )
+  (dropout): Dropout(p=0.0, inplace=False)
+  (lm_head): Linear(in_features=1024, out_features=151, bias=True)
+)
+
+/scratch/work/palp3/myenv/lib/python3.11/site-packages/accelerate/accelerator.py:488: FutureWarning: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead.
+  self.scaler = torch.cuda.amp.GradScaler(**kwargs)
+max_steps is given, it will override any value given in num_train_epochs
+08/22/2024 14:51:18 - 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%|          | 0/36 [00:00<?, ?it/s]
  6%|▌         | 2/36 [00:01<00:27,  1.23it/s]
  8%|▊         | 3/36 [00:02<00:34,  1.04s/it]
 11%|█         | 4/36 [00:04<00:42,  1.33s/it]
 14%|█▍        | 5/36 [00:06<00:44,  1.42s/it]
 17%|█▋        | 6/36 [00:07<00:42,  1.41s/it]
 19%|█▉        | 7/36 [00:08<00:35,  1.24s/it]
 22%|██▏       | 8/36 [00:09<00:27,  1.01it/s]
 25%|██▌       | 9/36 [00:09<00:22,  1.18it/s]
 28%|██▊       | 10/36 [00:10<00:21,  1.23it/s]
 31%|███       | 11/36 [00:11<00:20,  1.19it/s]
 33%|███▎      | 12/36 [00:12<00:19,  1.21it/s]
 36%|███▌      | 13/36 [00:12<00:18,  1.27it/s]
 39%|███▉      | 14/36 [00:13<00:15,  1.46it/s]
 42%|████▏     | 15/36 [00:13<00:12,  1.65it/s]
 44%|████▍     | 16/36 [00:14<00:11,  1.81it/s]
 47%|████▋     | 17/36 [00:14<00:09,  1.91it/s]
 50%|█████     | 18/36 [00:15<00:09,  1.85it/s]
 53%|█████▎    | 19/36 [00:15<00:09,  1.75it/s]
 56%|█████▌    | 20/36 [00:16<00:08,  1.81it/s]
 58%|█████▊    | 21/36 [00:16<00:07,  1.95it/s]
 61%|██████    | 22/36 [00:17<00:07,  1.96it/s]
 64%|██████▍   | 23/36 [00:17<00:06,  1.92it/s]
 67%|██████▋   | 24/36 [00:18<00:06,  1.92it/s]
 69%|██████▉   | 25/36 [00:18<00:06,  1.81it/s]
 72%|███████▏  | 26/36 [00:19<00:05,  1.84it/s]
 75%|███████▌  | 27/36 [00:19<00:04,  1.94it/s]
 78%|███████▊  | 28/36 [00:20<00:05,  1.59it/s]
 81%|████████  | 29/36 [00:22<00:06,  1.06it/s]
 83%|████████▎ | 30/36 [00:23<00:06,  1.11s/it]
 86%|████████▌ | 31/36 [00:25<00:06,  1.38s/it]
 89%|████████▉ | 32/36 [00:26<00:04,  1.15s/it]
 92%|█████████▏| 33/36 [00:27<00:02,  1.02it/s]
 94%|█████████▍| 34/36 [00:27<00:01,  1.18it/s]
 97%|█████████▋| 35/36 [00:28<00:00,  1.34it/s]
+Printing predictions for a few samples:
+Sample 1:
+  Reference: हम उनका उपयोग ऐसे ही कर सकते हैं या आवश्यकता अनुसार कुछ बदलाव करके उपयोग कर सकते हैं
+######
+
+
+  Prediction: 
+
+
+
+Sample 2:
+  Reference: अतः शीर्षक इस तरह से जोड़ सकते हैं
+######
+
+
+  Prediction: 
+
+
+
+Sample 3:
+  Reference: प्रेसेंटेशन के अंत में आपने स्लाइड की एक कॉपी बना ली है
+######
+
+
+  Prediction: 
+
+
+
+Sample 4:
+  Reference: चलिए अब फोंट्स और फोंट्स को फॉर्मेट करने के कुछ तरीके देखते हैं
+######
+
+
+  Prediction: 
+
+
+
+Sample 5:
+  Reference: यह एक डायलॉग बॉक्स खोलेगा जिसमें हम अपनी आवश्यकतानुसार फॉन्ट स्टाइल और साइज़ सेट कर सकते हैं
+######
+
+
+  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 metrics *****
+  eval_cer                    =        1.0
+  eval_loss                   =        nan
+  eval_model_preparation_time =     0.0044
+  eval_runtime                = 0:00:40.62
+  eval_samples                =        572
+  eval_samples_per_second     =     14.081
+  eval_steps_per_second       =      0.886
+  eval_wer                    =        1.0
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+

evalonlyhinglish_indicwav2vec_MUCS_warmup500_s300shuff100_2142224.out

@@ -0,0 +1,44 @@
+wandb: Currently logged in as: priyanshi-pal (priyanshipal). Use `wandb login --relogin` to force relogin
+wandb: wandb version 0.17.7 is available!  To upgrade, please run:
+wandb:  $ pip install wandb --upgrade
+wandb: Tracking run with wandb version 0.17.6
+wandb: Run data is saved locally in /scratch/elec/t405-puhe/p/palp3/MUCS/wandb/run-20240822_144249-be92xk0e
+wandb: Run `wandb offline` to turn off syncing.
+wandb: Syncing run eval_pd2000_s300_shuff100_hindi
+wandb: ⭐️ View project at https://wandb.ai/priyanshipal/huggingface
+wandb: 🚀 View run at https://wandb.ai/priyanshipal/huggingface/runs/be92xk0e
+/scratch/work/palp3/myenv/lib/python3.11/site-packages/transformers/training_args.py:1525: FutureWarning: `evaluation_strategy` is deprecated and will be removed in version 4.46 of 🤗 Transformers. Use `eval_strategy` instead
+  warnings.warn(
+
+Traceback (most recent call last):
+  File "/scratch/work/palp3/myenv/lib/python3.11/site-packages/datasets/builder.py", line 1997, in _prepare_split_single
+    for _, table in generator:
+  File "/scratch/work/palp3/myenv/lib/python3.11/site-packages/datasets/packaged_modules/json/json.py", line 98, in _generate_tables
+    dataset = dataset[self.config.field]
+              ~~~~~~~^^^^^^^^^^^^^^^^^^^
+KeyError: 'test'
+
+The above exception was the direct cause of the following exception:
+
+Traceback (most recent call last):
+  File "/scratch/elec/puhe/p/palp3/MUCS/eval_script_indicwav2vec.py", line 790, in <module>
+    main()
+  File "/scratch/elec/puhe/p/palp3/MUCS/eval_script_indicwav2vec.py", line 427, in main
+    raw_datasets["eval"] = load_dataset(
+                           ^^^^^^^^^^^^^
+  File "/scratch/work/palp3/myenv/lib/python3.11/site-packages/datasets/load.py", line 2616, in load_dataset
+    builder_instance.download_and_prepare(
+  File "/scratch/work/palp3/myenv/lib/python3.11/site-packages/datasets/builder.py", line 1029, in download_and_prepare
+    self._download_and_prepare(
+  File "/scratch/work/palp3/myenv/lib/python3.11/site-packages/datasets/builder.py", line 1124, in _download_and_prepare
+    self._prepare_split(split_generator, **prepare_split_kwargs)
+  File "/scratch/work/palp3/myenv/lib/python3.11/site-packages/datasets/builder.py", line 1884, in _prepare_split
+    for job_id, done, content in self._prepare_split_single(
+  File "/scratch/work/palp3/myenv/lib/python3.11/site-packages/datasets/builder.py", line 2040, in _prepare_split_single
+    raise DatasetGenerationError("An error occurred while generating the dataset") from e
+datasets.exceptions.DatasetGenerationError: An error occurred while generating the dataset
+wandb: - 0.005 MB of 0.005 MB uploaded
+wandb: ⭐️ View project at: https://wandb.ai/priyanshipal/huggingface
+wandb: Synced 6 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)
+wandb: Find logs at: ./wandb/run-20240822_144249-be92xk0e/logs
+wandb: WARNING The new W&B backend becomes opt-out in version 0.18.0; try it out with `wandb.require("core")`! See https://wandb.me/wandb-core for more information.

indicwav2vec_MUCS_warmup500_s300shuff100_2130813.out

@@ -1368,3 +1368,99 @@ last prediction string लता द्वारा अनुवादित ह
 /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<01:04,  3.03it/s]
  2%|▏         | 3/196 [00:01<01:31,  2.12it/s]
  2%|▏         | 4/196 [00:02<01:51,  1.72it/s]
  3%|▎         | 5/196 [00:02<02:05,  1.52it/s]
  3%|▎         | 6/196 [00:03<02:22,  1.33it/s]
  4%|▎         | 7/196 [00:04<02:25,  1.30it/s]
  4%|▍         | 8/196 [00:05<02:36,  1.20it/s]
  5%|▍         | 9/196 [00:07<03:28,  1.12s/it]
  5%|▌         | 10/196 [00:09<04:01,  1.30s/it]
  6%|▌         | 11/196 [00:10<04:34,  1.48s/it]
  6%|▌         | 12/196 [00:12<04:40,  1.53s/it]
  7%|▋         | 13/196 [00:13<04:02,  1.33s/it]
  7%|▋         | 14/196 [00:14<03:25,  1.13s/it]
  8%|▊         | 15/196 [00:14<02:54,  1.04it/s]
  8%|▊         | 16/196 [00:15<02:43,  1.10it/s]
  9%|▊         | 17/196 [00:16<02:43,  1.09it/s]
  9%|▉         | 18/196 [00:17<03:07,  1.06s/it]
 10%|▉         | 19/196 [00:19<03:56,  1.34s/it]
 10%|█         | 20/196 [00:21<04:07,  1.41s/it]
 11%|█         | 21/196 [00:22<04:14,  1.45s/it]
 11%|█         | 22/196 [00:24<03:57,  1.37s/it]
 12%|█▏        | 23/196 [00:24<03:29,  1.21s/it]
 12%|█▏        | 24/196 [00:25<02:49,  1.01it/s]
 13%|█▎        | 25/196 [00:25<02:27,  1.16it/s]
 13%|█▎        | 26/196 [00:26<02:11,  1.29it/s]
 14%|█▍        | 27/196 [00:27<02:01,  1.39it/s]
 14%|█▍        | 28/196 [00:27<01:56,  1.44it/s]
 15%|█▍        | 29/196 [00:28<01:57,  1.42it/s]
 15%|█▌        | 30/196 [00:29<01:55,  1.44it/s]
 16%|█▌        | 31/196 [00:29<01:44,  1.59it/s]
 16%|█▋        | 32/196 [00:30<01:44,  1.56it/s]
 17%|█▋        | 33/196 [00:31<01:59,  1.37it/s]
 17%|█▋        | 34/196 [00:32<02:24,  1.12it/s]
 18%|█▊        | 35/196 [00:33<02:35,  1.04it/s]
 18%|█▊        | 36/196 [00:34<02:52,  1.08s/it]
 19%|█▉        | 37/196 [00:35<02:46,  1.05s/it]
 19%|█▉        | 38/196 [00:36<02:35,  1.02it/s]
 20%|█▉        | 39/196 [00:37<02:22,  1.10it/s]
 20%|██        | 40/196 [00:38<02:13,  1.17it/s]
 21%|██        | 41/196 [00:38<02:02,  1.27it/s]
 21%|██▏       | 42/196 [00:39<01:57,  1.31it/s]
 22%|██▏       | 43/196 [00:40<01:54,  1.34it/s]
 22%|██▏       | 44/196 [00:40<01:49,  1.39it/s]
 23%|██▎       | 45/196 [00:41<01:43,  1.46it/s]
 23%|██▎       | 46/196 [00:42<01:38,  1.53it/s]
 24%|██▍       | 47/196 [00:42<01:37,  1.53it/s]
 24%|██▍       | 48/196 [00:43<01:33,  1.58it/s]
 25%|██▌       | 49/196 [00:44<01:32,  1.59it/s]
 26%|██▌       | 50/196 [00:44<01:31,  1.60it/s]
 26%|██▌       | 51/196 [00:45<01:28,  1.64it/s]
 27%|██▋       | 52/196 [00:45<01:30,  1.58it/s]
 27%|██▋       | 53/196 [00:46<01:30,  1.57it/s]
 28%|██▊       | 54/196 [00:47<01:30,  1.57it/s]
 28%|██▊       | 55/196 [00:48<01:38,  1.43it/s]
 29%|██▊       | 56/196 [00:48<01:46,  1.32it/s]
 29%|██▉       | 57/196 [00:49<01:51,  1.25it/s]
 30%|██▉       | 58/196 [00:50<01:52,  1.23it/s]
 30%|███       | 59/196 [00:51<01:49,  1.25it/s]
 31%|███       | 60/196 [00:51<01:38,  1.39it/s]
 31%|███       | 61/196 [00:52<01:32,  1.46it/s]
 32%|███▏      | 62/196 [00:53<01:33,  1.43it/s]
 32%|███▏      | 63/196 [00:54<01:34,  1.40it/s]
 33%|███▎      | 64/196 [00:54<01:34,  1.40it/s]
 33%|███▎      | 65/196 [00:55<01:33,  1.40it/s]
 34%|███▎      | 66/196 [00:56<01:38,  1.32it/s]
 34%|███▍      | 67/196 [00:57<01:40,  1.29it/s]
 35%|███▍      | 68/196 [00:58<01:51,  1.15it/s]
 35%|███▌      | 69/196 [00:59<01:48,  1.17it/s]
 36%|███▌      | 70/196 [00:59<01:41,  1.24it/s]
 36%|███▌      | 71/196 [01:00<01:34,  1.32it/s]
 37%|███▋      | 72/196 [01:01<01:28,  1.39it/s]
 37%|███▋      | 73/196 [01:01<01:21,  1.51it/s]
 38%|███▊      | 74/196 [01:02<01:17,  1.58it/s]
 38%|███▊      | 75/196 [01:02<01:15,  1.60it/s]
 39%|███▉      | 76/196 [01:03<01:13,  1.63it/s]
 39%|███▉      | 77/196 [01:04<01:17,  1.54it/s]
 40%|███▉      | 78/196 [01:04<01:18,  1.50it/s]
 40%|████      | 79/196 [01:05<01:17,  1.51it/s]
 41%|████      | 80/196 [01:06<01:21,  1.42it/s]
 41%|████▏     | 81/196 [01:06<01:21,  1.40it/s]
 42%|████▏     | 82/196 [01:07<01:20,  1.42it/s]
 42%|████▏     | 83/196 [01:08<01:22,  1.37it/s]
 43%|████▎     | 84/196 [01:09<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 [01:11<01:21,  1.34it/s]
 45%|████▍     | 88/196 [01:12<01:23,  1.29it/s]
 45%|████▌     | 89/196 [01:13<01:24,  1.26it/s]
 46%|████▌     | 90/196 [01:13<01:22,  1.29it/s]
 46%|████▋     | 91/196 [01:14<01:17,  1.35it/s]
 47%|████▋     | 92/196 [01:15<01:14,  1.40it/s]
 47%|████▋     | 93/196 [01:16<01:18,  1.31it/s]
 48%|████▊     | 94/196 [01:16<01:16,  1.33it/s]
 48%|████▊     | 95/196 [01:17<01:15,  1.34it/s]
 49%|████▉     | 96/196 [01:18<01:17,  1.28it/s]
 49%|████▉     | 97/196 [01:19<01:13,  1.34it/s]
 50%|█████     | 98/196 [01:19<01:14,  1.31it/s]
 51%|█████     | 99/196 [01:20<01:08,  1.41it/s]
 51%|█████     | 100/196 [01:20<01:00,  1.58it/s]
 52%|█████▏    | 101/196 [01:21<00:58,  1.61it/s]
 52%|█████▏    | 102/196 [01:22<01:02,  1.50it/s]
 53%|█████▎    | 103/196 [01:23<01:08,  1.37it/s]
 53%|█████▎    | 104/196 [01:24<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 [01:26<01:08,  1.30it/s]
 55%|█████▌    | 108/196 [01:26<01:00,  1.44it/s]
 56%|█████▌    | 109/196 [01:27<00:57,  1.50it/s]
 56%|█████▌    | 110/196 [01:28<00:56,  1.52it/s]
 57%|█████▋    | 111/196 [01:28<00:56,  1.51it/s]
 57%|█████▋    | 112/196 [01:29<00:57,  1.45it/s]
 58%|█████▊    | 113/196 [01:30<00:56,  1.47it/s]
 58%|█████▊    | 114/196 [01:30<00:52,  1.56it/s]
 59%|█████▊    | 115/196 [01:31<00:51,  1.58it/s]
 59%|█████▉    | 116/196 [01:32<00:50,  1.59it/s]
 60%|█████▉    | 117/196 [01:32<00:46,  1.70it/s]
 60%|██████    | 118/196 [01:32<00:41,  1.86it/s]
 61%|██████    | 119/196 [01:33<00:44,  1.71it/s]
 61%|██████    | 120/196 [01:34<00:46,  1.65it/s]
 62%|██████▏   | 121/196 [01:34<00:46,  1.61it/s]
 62%|██████▏   | 122/196 [01:35<00:47,  1.57it/s]
 63%|██████▎   | 123/196 [01:36<00:45,  1.60it/s]
 63%|██████▎   | 124/196 [01:36<00:46,  1.56it/s]
 64%|██████▍   | 125/196 [01:37<00:45,  1.55it/s]
 64%|██████▍   | 126/196 [01:38<00:51,  1.36it/s]
 65%|██████▍   | 127/196 [01:39<00:49,  1.40it/s]
 65%|██████▌   | 128/196 [01:39<00:46,  1.47it/s]
 66%|██████▌   | 129/196 [01:40<00:44,  1.49it/s]
 66%|██████▋   | 130/196 [01:41<00:45,  1.46it/s]
 67%|██████▋   | 131/196 [01:41<00:44,  1.47it/s]
 67%|██████▋   | 132/196 [01:42<00:40,  1.57it/s]
 68%|██████▊   | 133/196 [01:42<00:40,  1.57it/s]
 68%|██████▊   | 134/196 [01:43<00:40,  1.53it/s]
 69%|██████▉   | 135/196 [01:44<00:39,  1.56it/s]
 69%|██████▉   | 136/196 [01:44<00:38,  1.56it/s]
 70%|██████▉   | 137/196 [01:45<00:37,  1.56it/s]
 70%|███████   | 138/196 [01:46<00:36,  1.57it/s]
 71%|███████   | 139/196 [01:46<00:37,  1.50it/s]
 71%|███████▏  | 140/196 [01:47<00:35,  1.56it/s]
 72%|███████▏  | 141/196 [01:48<00:34,  1.58it/s]
 72%|███████▏  | 142/196 [01:48<00:34,  1.54it/s]
 73%|███████▎  | 143/196 [01:49<00:35,  1.49it/s]
 73%|███████▎  | 144/196 [01:50<00:33,  1.56it/s]
 74%|███████▍  | 145/196 [01:50<00:30,  1.68it/s]
 74%|███████▍  | 146/196 [01:51<00:28,  1.74it/s]
 75%|███████▌  | 147/196 [01:51<00:28,  1.75it/s]
 76%|███████▌  | 148/196 [01:52<00:27,  1.73it/s]
 76%|███████▌  | 149/196 [01:52<00:25,  1.82it/s]
 77%|███████▋  | 150/196 [01:53<00:27,  1.67it/s]
 77%|███████▋  | 151/196 [01:54<00:28,  1.61it/s]
 78%|███████▊  | 152/196 [01:54<00:27,  1.60it/s]
 78%|███████▊  | 153/196 [01:55<00:26,  1.60it/s]
 79%|███████▊  | 154/196 [01:56<00:26,  1.59it/s]
 79%|███████▉  | 155/196 [01:56<00:27,  1.48it/s]
 80%|███████▉  | 156/196 [01:57<00:29,  1.34it/s]
 80%|████████  | 157/196 [01:58<00:30,  1.29it/s]
 81%|████████  | 158/196 [01:59<00:26,  1.43it/s]
 81%|████████  | 159/196 [01:59<00:24,  1.53it/s]
 82%|████████▏ | 160/196 [02:00<00:23,  1.56it/s]
 82%|████████▏ | 161/196 [02:00<00:22,  1.53it/s]
 83%|████████▎ | 162/196 [02:01<00:21,  1.55it/s]
 83%|████████▎ | 163/196 [02:02<00:20,  1.57it/s]
 84%|████████▎ | 164/196 [02:02<00:20,  1.58it/s]
 84%|████████▍ | 165/196 [02:03<00:20,  1.53it/s]
 85%|████████▍ | 166/196 [02:04<00:19,  1.57it/s]
 85%|███████���▌ | 167/196 [02:04<00:18,  1.60it/s]
 86%|████████▌ | 168/196 [02:05<00:16,  1.69it/s]
 86%|████████▌ | 169/196 [02:05<00:16,  1.60it/s]
 87%|████████▋ | 170/196 [02:06<00:17,  1.51it/s]
 87%|████████▋ | 171/196 [02:07<00:16,  1.51it/s]
 88%|████████▊ | 172/196 [02:08<00:16,  1.49it/s]
 88%|████████▊ | 173/196 [02:08<00:15,  1.49it/s]
 89%|████████▉ | 174/196 [02:09<00:15,  1.42it/s]
 89%|████████▉ | 175/196 [02:10<00:18,  1.14it/s]
 90%|████████▉ | 176/196 [02:13<00:26,  1.30s/it]
 90%|█████████ | 177/196 [02:14<00:28,  1.48s/it]
 91%|█████████ | 178/196 [02:17<00:30,  1.67s/it]
 91%|█████████▏| 179/196 [02:18<00:28,  1.66s/it]
 92%|█████████▏| 180/196 [02:19<00:21,  1.37s/it]
 92%|█████████▏| 181/196 [02:20<00:17,  1.16s/it]
 93%|█████████▎| 182/196 [02:20<00:14,  1.01s/it]
 93%|█████████▎| 183/196 [02:21<00:12,  1.01it/s]
 94%|█████████▍| 184/196 [02:22<00:10,  1.13it/s]
 94%|█████████▍| 185/196 [02:23<00:09,  1.17it/s]
 95%|█████████▍| 186/196 [02:23<00:08,  1.17it/s]
 95%|█████████▌| 187/196 [02:24<00:07,  1.26it/s]
 96%|█████████▌| 188/196 [02:25<00:05,  1.34it/s]
 96%|█████████▋| 189/196 [02:25<00:05,  1.38it/s]
 97%|█████████▋| 190/196 [02:26<00:04,  1.45it/s]
 97%|█████████▋| 191/196 [02:27<00:03,  1.52it/s]
 98%|█████████▊| 192/196 [02:27<00:02,  1.49it/s]
 98%|█████████▊| 193/196 [02:28<00:02,  1.48it/s]
 99%|█████████▉| 194/196 [02:29<00:01,  1.51it/s]
 99%|█████████▉| 195/196 [02:29<00:00,  1.56it/s]
+Printing predictions for a few samples:
+Sample 1:
+  Reference: लिबर ऑफिस impress में एक प्रस्तुति document बनाना और बुनियादी formatting के इस spoken tutorial में आपका स्वागत है
+######
+
+
+  Prediction: liber offिc impess में एक प्रस्तुति document बनाना और बुनियादी formating के इस spoken tutorial में आपका स्वागहै
+
+
+
+Sample 2:
+  Reference: इस tutorial में हम impress window के भागों के बारे में सीखेंगे और कैसे स्लाइड इन्सर्ट करें और कॉपी करें फॉन्ट तथा फॉन्ट को फॉर्मेट करना सीखेंगे
+######
+
+
+  Prediction: इस tutorial में हम impres windw के भागों के बारे में सीखेंगे और कैसे slide insert करें और copy करें font तथा font को format करना सीखेंगे
+
+
+
+Sample 3:
+  Reference: यहाँ हम अपने ऑपरेटिंग सिस्टम के रूप में gnu/linux और लिबरऑफिस वर्जन 334 का उपयोग कर रहे हैं
+######
+
+
+  Prediction: यहाँ हम अपने operating system के रूप में gnu linuक और liber ffic version 334 का उपयोग कर रे हैं
+
+
+
+Sample 4:
+  Reference: चलिए अपनी प्रस्तुति प्रेजैटेशन sample impress open करते हैं जिसे पिछले tutorial में बनाया था
+######
+
+
+  Prediction: चलिए अपनी प्रस्तुति sampl impres open करते हैं जि
+
+
+
+Sample 5:
+  Reference: चलिए देखते हैं कि screen पर क्या क्या है
+######
+
+
+  Prediction: चलिए देखते हैं कि scren 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 लता द्वारा अनुवादित है आई आई टी मुमं्बई की ओर से मैं रवि कुमार अब आपसे विदा लेता हूँ हमसे जुड़ने के लिए धन्यवाद
+***** eval metrics *****
+  epoch                   =        1.6
+  eval_cer                =     0.3096
+  eval_loss               =     1.5066
+  eval_runtime            = 0:02:39.31
+  eval_samples            =       3136
+  eval_samples_per_second =     19.684
+  eval_steps_per_second   =       1.23
+  eval_wer                =     0.4357
+wandb: - 0.007 MB of 0.007 MB uploaded
+wandb: Run history:
+wandb:                eval/cer ▁▁
+wandb:               eval/loss ▁▁
+wandb:            eval/runtime █▁
+wandb: eval/samples_per_second ▁█
+wandb:   eval/steps_per_second ▁█
+wandb:                eval/wer ▁▁
+wandb:             train/epoch ▁▁▁▂▂▂▂▂▂▃▃▃▃▃▄▄▄▄▄▄▅▅▅▅▅▅▆▆▆▆▆▇▇▇▇▇▇███
+wandb:       train/global_step ▁▁▁▂▂▂▂▂▂▃▃▃▃▃▄▄▄▄▄▄▅▅▅▅▅▅▆▆▆▆▆▇▇▇▇▇▇███
+wandb:         train/grad_norm ▃▃█▂▇▁▂▂▂▁▁▁▁▁▁▁▁▁▁▁▁▁▂▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁
+wandb:     train/learning_rate ▁▁▂▂▂▃▃▃▄▄▅▅▅▆▆▆▇▇▇███▇▇▇▆▆▅▅▅▄▄▄▃▃▃▂▂▁▁
+wandb:              train/loss █▆▅▂▂▂▂▂▂▂▂▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁
+wandb: 
+wandb: Run summary:
+wandb:                 eval/cer 0.30955
+wandb:                eval/loss 1.50663
+wandb:             eval/runtime 159.3193
+wandb:  eval/samples_per_second 19.684
+wandb:    eval/steps_per_second 1.23
+wandb:                 eval/wer 0.43572
+wandb:               total_flos 6.212261523683712e+18
+wandb:              train/epoch 1.6
+wandb:        train/global_step 1000
+wandb:          train/grad_norm 0.9419
+wandb:      train/learning_rate 1e-05
+wandb:               train/loss 0.9856
+wandb:               train_loss 3.21393
+wandb:            train_runtime 2133.1271
+wandb: train_samples_per_second 15.001
+wandb:   train_steps_per_second 0.469
+wandb: 
+wandb: 🚀 View run elated-pine-27 at: https://wandb.ai/priyanshipal/huggingface/runs/0evkescz
+wandb: ⭐️ View project at: https://wandb.ai/priyanshipal/huggingface
+wandb: Synced 6 W&B file(s), 0 media file(s), 1 artifact file(s) and 0 other file(s)
+wandb: Find logs at: ./wandb/run-20240821_155449-0evkescz/logs
+wandb: WARNING The new W&B backend becomes opt-out in version 0.18.0; try it out with `wandb.require("core")`! See https://wandb.me/wandb-core for more information.

json/default-b60d5edd0f197c71/0.0.0/7483f22a71512872c377524b97484f6d20c275799bb9e7cd8fb3198178d8220a/dataset_info.json

@@ -0,0 +1 @@
+{"description": "", "citation": "", "homepage": "", "license": "", "features": {"audio_id": {"dtype": "string", "_type": "Value"}, "audio_paths": {"dtype": "string", "_type": "Value"}, "transcriptions": {"dtype": "string", "_type": "Value"}}, "builder_name": "json", "dataset_name": "json", "config_name": "default", "version": {"version_str": "0.0.0", "major": 0, "minor": 0, "patch": 0}, "splits": {"train": {"name": "train", "num_bytes": 159776, "num_examples": 572, "dataset_name": "json"}}, "download_checksums": {"/m/triton/scratch/elec/puhe/p/palp3/MUCS/mucs_language_segregated_data/MUCS_test_languagesep_data.json": {"num_bytes": 1275544, "checksum": null}}, "download_size": 1275544, "dataset_size": 159776, "size_in_bytes": 1435320}

json/default-b60d5edd0f197c71/0.0.0/7483f22a71512872c377524b97484f6d20c275799bb9e7cd8fb3198178d8220a/json-train.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f67abacdef72568fdccdc70e54cc80c5aca72a7c217cf5c533dcdd9be5ca20b5
+size 160568

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9367c78a92aef3076de01353e7f63733eb3273ffbca6c59957741bf6a4155549
+oid sha256:6d6e542b15e77cd1bb8a7693945d939d7b6324a0178a2a54a151c7870a9a3a70
 size 1262426580

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aeac58d8964b49d915038731c28a91ee0d56a3958c02bf5737260d7c08c53eba
+oid sha256:fb6b542d4c167a87206ca85c8c0bf1f22fdbd339b4288aa2bc0c42cdd80202f8
 size 5432