End of training

README.md

@@ -0,0 +1,60 @@
+---
+tags:
+- generated_from_trainer
+model-index:
+- name: eval_cache_hindi_only
+  results: []
+---
+
+<!-- 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/upry9j53)
+# eval_cache_hindi_only
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- eval_loss: 2.2188
+- eval_model_preparation_time: 0.0045
+- eval_cer: 0.4569
+- eval_wer: 0.5264
+- eval_runtime: 31.2077
+- eval_samples_per_second: 18.329
+- eval_steps_per_second: 1.154
+- step: 0
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0006
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 300
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- training_steps: 1000
+- mixed_precision_training: Native AMP
+
+### Framework versions
+
+- Transformers 4.43.1
+- Pytorch 2.4.0
+- Datasets 2.20.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,10 @@
+{
+    "eval_cer": 0.45689757252812313,
+    "eval_loss": 2.218759059906006,
+    "eval_model_preparation_time": 0.0045,
+    "eval_runtime": 31.2077,
+    "eval_samples": 572,
+    "eval_samples_per_second": 18.329,
+    "eval_steps_per_second": 1.154,
+    "eval_wer": 0.5264004680415387
+}

config.json

@@ -0,0 +1,109 @@
+{
+  "_name_or_path": "/scratch/elec/puhe/p/palp3/MUCS/indicwav2vec_outputs/pd_warmup_500/s300_shuff100",
+  "activation_dropout": 0.0,
+  "adapter_attn_dim": null,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.3,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 256,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": true,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": true,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.3,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.2,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "model_type": "wav2vec2",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 16,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 148,
+  "proj_codevector_dim": 256,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.43.1",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 151,
+  "xvector_output_dim": 512
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "eval_cer": 0.45689757252812313,
+    "eval_loss": 2.218759059906006,
+    "eval_model_preparation_time": 0.0045,
+    "eval_runtime": 31.2077,
+    "eval_samples": 572,
+    "eval_samples_per_second": 18.329,
+    "eval_steps_per_second": 1.154,
+    "eval_wer": 0.5264004680415387
+}

evalonlyhindi_indicwav2vec_MUCS_warmup500_s300shuff100_2144517.out

@@ -0,0 +1,309 @@
+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_174142-upry9j53
+wandb: Run `wandb offline` to turn off syncing.
+wandb: Syncing run eval_pd20000_w500_s300_shuff100_hinglish
+wandb: ⭐️ View project at https://wandb.ai/priyanshipal/huggingface
+wandb: 🚀 View run at https://wandb.ai/priyanshipal/huggingface/runs/upry9j53
+/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/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(
+/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
+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=0.3, 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=0.2, 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=0.2, 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=0.2, 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)
+)
+check the eval set length 572
+08/22/2024 17:41:50 - 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<00:23,  1.43it/s]
  8%|▊         | 3/36 [00:02<00:31,  1.04it/s]
 11%|█         | 4/36 [00:04<00:40,  1.26s/it]
 14%|█▍        | 5/36 [00:06<00:42,  1.36s/it]
 17%|█▋        | 6/36 [00:07<00:40,  1.36s/it]
 19%|█▉        | 7/36 [00:08<00:35,  1.21s/it]
 22%|██▏       | 8/36 [00:08<00:27,  1.04it/s]
 25%|██▌       | 9/36 [00:09<00:22,  1.20it/s]
 28%|██▊       | 10/36 [00:09<00:20,  1.24it/s]
 31%|███       | 11/36 [00:10<00:20,  1.21it/s]
 33%|███▎      | 12/36 [00:11<00:19,  1.22it/s]
 36%|███▌      | 13/36 [00:12<00:17,  1.31it/s]
 39%|███▉      | 14/36 [00:12<00:14,  1.50it/s]
 42%|████▏     | 15/36 [00:13<00:12,  1.68it/s]
 44%|████▍     | 16/36 [00:13<00:10,  1.83it/s]
 47%|████▋     | 17/36 [00:14<00:09,  1.92it/s]
 50%|█████     | 18/36 [00:14<00:09,  1.86it/s]
 53%|█████▎    | 19/36 [00:15<00:09,  1.78it/s]
 56%|█████▌    | 20/36 [00:15<00:08,  1.83it/s]
 58%|█████▊    | 21/36 [00:16<00:07,  1.97it/s]
 61%|██████    | 22/36 [00:16<00:07,  1.97it/s]
 64%|██████▍   | 23/36 [00:17<00:06,  1.94it/s]
 67%|██████▋   | 24/36 [00:17<00:06,  1.93it/s]
 69%|██████▉   | 25/36 [00:18<00:05,  1.85it/s]
 72%|███████▏  | 26/36 [00:18<00:05,  1.87it/s]
 75%|███████▌  | 27/36 [00:19<00:04,  1.96it/s]
 78%|███████▊  | 28/36 [00:20<00:04,  1.63it/s]
 81%|████████  | 29/36 [00:21<00:06,  1.07it/s]
 83%|████████▎ | 30/36 [00:23<00:06,  1.08s/it]
 86%|████████▌ | 31/36 [00:25<00:06,  1.35s/it]
 89%|████████▉ | 32/36 [00:25<00:04,  1.12s/it]
 92%|█████████▏| 33/36 [00:26<00:02,  1.04it/s]
 94%|█████████▍| 34/36 [00:26<00:01,  1.20it/s]
 97%|█████████▋| 35/36 [00:27<00:00,  1.35it/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: हम उनका उपयोग ऐसे ही कर सकते हैं
+
+
+
+Sample 2:
+  Reference: अतः शीर्षक इस तरह से जोड़ सकते हैं
+######
+
+
+  Prediction: अतः शीर्ष है
+
+
+
+Sample 3:
+  Reference: प्रेसेंटेशन के अंत में आपने स्लाइड की एक कॉपी बना ली है
+######
+
+
+  Prediction: presentation के अंत में आपने स ैंैं
+
+
+
+Sample 4:
+  Reference: चलिए अब फोंट्स और फोंट्स को फॉर्मेट करने के कुछ तरीके देखते हैं
+######
+
+
+  Prediction: चलिए अब fonts और fonts को format करने के कुछ तरीके देेहं
+
+
+
+Sample 5:
+  Reference: यह एक डायलॉग बॉक्स खोलेगा जिसमें हम अपनी आवश्यकतानुसार फॉन्ट स्टाइल और साइज़ सेट कर सकते हैं
+######
+
+
+  Prediction: यह एक dialog box खोलेगा जिसमें हम अपनी आवश्यकत हैहै
+
+
+
+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 मुmबई की ओर से मैं रवि कुमार अब आपसे विदा लेता हूँ हमसे जुड़ने के लिए धन्यवाद
+***** eval metrics *****
+  eval_cer                    =     0.4569
+  eval_loss                   =     2.2188
+  eval_model_preparation_time =     0.0045
+  eval_runtime                = 0:00:31.20
+  eval_samples                =        572
+  eval_samples_per_second     =     18.329
+  eval_steps_per_second       =      1.154
+  eval_wer                    =     0.5264
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08de7da709cb1c87182ea525062fcd525beeade5ce32613467ec0bcc59e40f04
+size 1262426580

preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0,
+  "processor_class": "Wav2Vec2Processor",
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d8d438794391e3bf26a9530b1ace42edaca09a85e6347831ad44994aa46da18
+size 5432