bengali_1B/trainer_push

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+normalized.csv filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,56 @@
+---
+license: cc-by-nc-4.0
+base_model: Umong/wav2vec2-large-mms-1b-bengali
+tags:
+- generated_from_trainer
+model-index:
+- name: Umong/wav2vec2-large-mms-1b-bengali
+  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. -->
+
+# Umong/wav2vec2-large-mms-1b-bengali
+
+This model is a fine-tuned version of [Umong/wav2vec2-large-mms-1b-bengali](https://huggingface.co/Umong/wav2vec2-large-mms-1b-bengali) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- eval_loss: 0.8979
+- eval_runtime: 77.1222
+- eval_samples_per_second: 6.483
+- eval_steps_per_second: 1.621
+- epoch: 0.84
+- step: 9000
+
+## 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: 2e-06
+- train_batch_size: 2
+- eval_batch_size: 4
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 2000
+- num_epochs: 1
+
+### Framework versions
+
+- Transformers 4.33.3
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.5
+- Tokenizers 0.13.3

config.json

@@ -0,0 +1,108 @@
+{
+  "_name_or_path": "Umong/wav2vec2-large-mms-1b-bengali",
+  "activation_dropout": 0.05,
+  "adapter_attn_dim": 16,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 1024,
+  "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": true,
+  "diversity_loss_weight": 100,
+  "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": 0.0,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.05,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.2,
+  "hidden_size": 1280,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.2,
+  "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": 0.1,
+  "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": 48,
+  "num_negatives": 100,
+  "output_hidden_size": 1280,
+  "pad_token_id": 63,
+  "proj_codevector_dim": 1024,
+  "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": "4.33.3",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 66,
+  "xvector_output_dim": 512
+}

dataset-overlaps-with-commonvoice-11-bn.log

@@ -0,0 +1,157 @@
+[{"stream_name":"stderr","time":9.00453959,"data":"[IPKernelApp] WARNING | Error in loading extension: bq_stats\n"}
+,{"stream_name":"stderr","time":9.0046337,"data":"Check your config files in /root/.ipython/profile_default\n"}
+,{"stream_name":"stderr","time":9.00466419,"data":"Traceback (most recent call last):\n"}
+,{"stream_name":"stderr","time":9.00467042,"data":"  File \"/opt/conda/lib/python3.10/site-packages/IPython/core/shellapp.py\", line 282, in init_extensions\n"}
+,{"stream_name":"stderr","time":9.00467969,"data":"    self.shell.extension_manager.load_extension(ext)\n"}
+,{"stream_name":"stderr","time":9.00468438,"data":"  File \"/opt/conda/lib/python3.10/site-packages/IPython/core/extensions.py\", line 76, in load_extension\n"}
+,{"stream_name":"stderr","time":9.00468905,"data":"    return self._load_extension(module_str)\n"}
+,{"stream_name":"stderr","time":9.00469301,"data":"  File \"/opt/conda/lib/python3.10/site-packages/IPython/core/extensions.py\", line 91, in _load_extension\n"}
+,{"stream_name":"stderr","time":9.00469716,"data":"    mod = import_module(module_str)\n"}
+,{"stream_name":"stderr","time":9.00470076,"data":"  File \"/opt/conda/lib/python3.10/importlib/__init__.py\", line 126, in import_module\n"}
+,{"stream_name":"stderr","time":9.00470429,"data":"    return _bootstrap._gcd_import(name[level:], package, level)\n"}
+,{"stream_name":"stderr","time":9.00470784,"data":"  File \"\u003cfrozen importlib._bootstrap\u003e\", line 1050, in _gcd_import\n"}
+,{"stream_name":"stderr","time":9.00471202,"data":"  File \"\u003cfrozen importlib._bootstrap\u003e\", line 1027, in _find_and_load\n"}
+,{"stream_name":"stderr","time":9.00471592,"data":"  File \"\u003cfrozen importlib._bootstrap\u003e\", line 1004, in _find_and_load_unlocked\n"}
+,{"stream_name":"stderr","time":9.0047199,"data":"ModuleNotFoundError: No module named 'bq_stats'\n"}
+,{"stream_name":"stdout","time":12.189450805,"data":"Downloading and preparing dataset common_voice/bn to /root/.cache/huggingface/datasets/mozilla-foundation___common_voice/bn/11.0.0/3f27acf10f303eac5b6fbbbe02495aeddb46ecffdb0a2fe3507fcfbf89094631...\n"}
+,{"stream_name":"stderr","time":282.186192879,"data":"\n"}
+,{"stream_name":"stderr","time":282.292363731,"data":"\rReading metadata...: 0it [00:00, ?it/s]\u001b[A\n"}
+,{"stream_name":"stderr","time":282.386399175,"data":"\rReading metadata...: 11398it [00:00, 113963.81it/s]\u001b[A\rReading metadata...: 16777it [00:00, 107248.43it/s]\n"}
+,{"stream_name":"stderr","time":291.233711451,"data":"\n"}
+,{"stream_name":"stderr","time":291.432171637,"data":"\rReading metadata...: 0it [00:00, ?it/s]\u001b[A\rReading metadata...: 8353it [00:00, 132338.47it/s]\n"}
+,{"stream_name":"stderr","time":294.545279107,"data":"\n"}
+,{"stream_name":"stderr","time":294.740125853,"data":"\rReading metadata...: 0it [00:00, ?it/s]\u001b[A\rReading metadata...: 8353it [00:00, 137305.01it/s]\n"}
+,{"stream_name":"stderr","time":298.394769736,"data":"\n"}
+,{"stream_name":"stderr","time":298.496171909,"data":"\rReading metadata...: 0it [00:00, ?it/s]\u001b[A\n"}
+,{"stream_name":"stderr","time":298.604225211,"data":"\rReading metadata...: 14119it [00:00, 141173.98it/s]\u001b[A\n"}
+,{"stream_name":"stderr","time":298.708220034,"data":"\rReading metadata...: 28237it [00:00, 134681.19it/s]\u001b[A\n"}
+,{"stream_name":"stderr","time":298.808317277,"data":"\rReading metadata...: 41726it [00:00, 132718.44it/s]\u001b[A\n"}
+,{"stream_name":"stderr","time":298.90815864,"data":"\rReading metadata...: 55106it [00:00, 133130.71it/s]\u001b[A\n"}
+,{"stream_name":"stderr","time":299.012041292,"data":"\rReading metadata...: 68773it [00:00, 134382.80it/s]\u001b[A\n"}
+,{"stream_name":"stderr","time":299.117872665,"data":"\rReading metadata...: 82218it [00:00, 132626.22it/s]\u001b[A\n"}
+,{"stream_name":"stderr","time":299.221650208,"data":"\rReading metadata...: 95488it [00:00, 130352.31it/s]\u001b[A\n"}
+,{"stream_name":"stderr","time":299.32609062,"data":"\rReading metadata...: 108533it [00:00, 128713.86it/s]\u001b[A\n"}
+,{"stream_name":"stderr","time":299.430928863,"data":"\rReading metadata...: 121412it [00:00, 126866.61it/s]\u001b[A\n"}
+,{"stream_name":"stderr","time":299.530856126,"data":"\rReading metadata...: 134105it [00:01, 125081.83it/s]\u001b[A\n"}
+,{"stream_name":"stderr","time":299.633776039,"data":"\rReading metadata...: 146905it [00:01, 125945.08it/s]\u001b[A\n"}
+,{"stream_name":"stderr","time":299.734081722,"data":"\rReading metadata...: 159506it [00:01, 124890.05it/s]\u001b[A\n"}
+,{"stream_name":"stderr","time":299.837771394,"data":"\rReading metadata...: 172505it [00:01, 126400.87it/s]\u001b[A\n"}
+,{"stream_name":"stderr","time":299.939560147,"data":"\rReading metadata...: 185152it [00:01, 124997.06it/s]\u001b[A\n"}
+,{"stream_name":"stderr","time":300.0414487,"data":"\rReading metadata...: 197658it [00:01, 124365.12it/s]\u001b[A\n"}
+,{"stream_name":"stderr","time":300.139746573,"data":"\rReading metadata...: 210414it [00:01, 125308.06it/s]\u001b[A\n"}
+,{"stream_name":"stderr","time":300.240470356,"data":"\rReading metadata...: 222996it [00:01, 125457.18it/s]\u001b[A\rReading metadata...: 225826it [00:01, 127471.88it/s]\n"}
+,{"stream_name":"stderr","time":433.997174478,"data":"\n"}
+,{"stream_name":"stderr","time":434.195508939,"data":"\rReading metadata...: 0it [00:00, ?it/s]\u001b[A\rReading metadata...: 6447it [00:00, 80059.80it/s]\n"}
+,{"stream_name":"stdout","time":437.937668012,"data":"Dataset common_voice downloaded and prepared to /root/.cache/huggingface/datasets/mozilla-foundation___common_voice/bn/11.0.0/3f27acf10f303eac5b6fbbbe02495aeddb46ecffdb0a2fe3507fcfbf89094631. Subsequent calls will reuse this data.\n"}
+,{"stream_name":"stdout","time":444.668977881,"data":"Split Name :  train\n"}
+,{"stream_name":"stdout","time":444.669015671,"data":"Total audios in commonvoice train:  16777\n"}
+,{"stream_name":"stdout","time":444.669026061,"data":"Total audios in train :  16041\n"}
+,{"stream_name":"stdout","time":444.669031571,"data":"Total audios in val :  0\n"}
+,{"stream_name":"stdout","time":444.669035791,"data":"--------------------------------------------------------------------------------\n"}
+,{"stream_name":"stdout","time":444.669039811,"data":"Split Name :  test\n"}
+,{"stream_name":"stdout","time":444.669044411,"data":"Total audios in commonvoice test:  8353\n"}
+,{"stream_name":"stdout","time":444.669048451,"data":"Total audios in train :  7531\n"}
+,{"stream_name":"stdout","time":444.669052721,"data":"Total audios in val :  0\n"}
+,{"stream_name":"stdout","time":444.669056741,"data":"--------------------------------------------------------------------------------\n"}
+,{"stream_name":"stdout","time":444.669060981,"data":"Split Name :  validation\n"}
+,{"stream_name":"stdout","time":444.669065171,"data":"Total audios in commonvoice validation:  8353\n"}
+,{"stream_name":"stdout","time":444.669069191,"data":"Total audios in train :  7769\n"}
+,{"stream_name":"stdout","time":444.669073661,"data":"Total audios in val :  0\n"}
+,{"stream_name":"stdout","time":444.669077531,"data":"--------------------------------------------------------------------------------\n"}
+,{"stream_name":"stdout","time":445.519689576,"data":"Split Name :  other\n"}
+,{"stream_name":"stdout","time":445.559222476,"data":"Total audios in commonvoice other:  225826\n"}
+,{"stream_name":"stdout","time":445.559279306,"data":"Total audios in train :  224996\n"}
+,{"stream_name":"stdout","time":445.559313656,"data":"Total audios in val :  0\n"}
+,{"stream_name":"stdout","time":445.559319516,"data":"--------------------------------------------------------------------------------\n"}
+,{"stream_name":"stdout","time":445.559323646,"data":"Split Name :  invalidated\n"}
+,{"stream_name":"stdout","time":445.559327506,"data":"Total audios in commonvoice invalidated:  6447\n"}
+,{"stream_name":"stdout","time":445.559332256,"data":"Total audios in train :  5627\n"}
+,{"stream_name":"stdout","time":445.559335886,"data":"Total audios in val :  0\n"}
+,{"stream_name":"stdout","time":445.559339526,"data":"--------------------------------------------------------------------------------\n"}
+,{"stream_name":"stdout","time":445.559342966,"data":"Total common voice audio :265756\n"}
+,{"stream_name":"stdout","time":445.559346556,"data":" Audios present here : 261964\n"}
+,{"stream_name":"stderr","time":445.560502156,"data":"\r  0%|          | 0/5 [00:00\u003c?, ?it/s]\r 20%|██        | 1/5 [00:00\u003c00:00,  6.84it/s]\r 60%|██████    | 3/5 [00:00\u003c00:00, 10.79it/s]\r100%|██████████| 5/5 [00:01\u003c00:00,  2.58it/s]\r100%|██████████| 5/5 [00:01\u003c00:00,  3.07it/s]\n"}
+,{"stream_name":"stderr","time":446.123441549,"data":"\r  0%|          | 0/5 [00:00\u003c?, ?it/s]\r 80%|████████  | 4/5 [00:00\u003c00:00,  8.48it/s]\r100%|██████████| 5/5 [00:00\u003c00:00, 10.24it/s]\n"}
+,{"stream_name":"stderr","time":447.040023925,"data":"\r0it [00:00, ?it/s]\r106171it [00:00, 1061592.05it/s]\r216964it [00:00, 1088775.74it/s]\r337425it [00:00, 1141613.17it/s]\r452967it [00:00, 1147016.53it/s]\r572951it [00:00, 1166016.06it/s]\r689553it [00:00, 1157771.60it/s]\r810008it [00:00, 1172950.29it/s]\r935257it [00:00, 1198143.09it/s]\r963636it [00:00, 1155136.54it/s]\n"}
+,{"stream_name":"stdout","time":453.23643988,"data":"Sentence :  এরা সবাই দাস হিসেবে একটি জাহাজে করে বিদেশে পাচার হচ্ছিল।\n"}
+,{"stream_name":"stdout","time":453.23650391,"data":"Common Voice audio :\n"}
+,{"stream_name":"stdout","time":453.432182231,"data":"Competition data audio :  ae1be00ad59d.mp3\n"}
+,{"stream_name":"stdout","time":453.783724884,"data":"--------------------------------------------------------------------------------\n"}
+,{"stream_name":"stdout","time":453.783783484,"data":"--------------------------------------------------------------------------------\n"}
+,{"stream_name":"stdout","time":453.783788414,"data":"Sentence :  তিনি জানান এই কাজ সুভাষ দত্ত করবে এবং রহমানকে তার সহকারী হিসেবে যোগ দিতে বলেন।\n"}
+,{"stream_name":"stdout","time":453.783794164,"data":"Common Voice audio :\n"}
+,{"stream_name":"stdout","time":453.815708834,"data":"Competition data audio :  2bfa78215372.mp3\n"}
+,{"stream_name":"stdout","time":454.228451986,"data":"--------------------------------------------------------------------------------\n"}
+,{"stream_name":"stdout","time":454.228507256,"data":"--------------------------------------------------------------------------------\n"}
+,{"stream_name":"stdout","time":454.228511766,"data":"Sentence :  এটি দক্ষিণ মিশরের একটি শহর।\n"}
+,{"stream_name":"stdout","time":454.228515496,"data":"Common Voice audio :\n"}
+,{"stream_name":"stdout","time":454.250528576,"data":"Competition data audio :  98f9873ba235.mp3\n"}
+,{"stream_name":"stdout","time":454.698182469,"data":"--------------------------------------------------------------------------------\n"}
+,{"stream_name":"stdout","time":454.698266699,"data":"--------------------------------------------------------------------------------\n"}
+,{"stream_name":"stdout","time":454.702478109,"data":"Sentence :  বর্তমানে এদের আবাসস্থল হুমকির মুখে।\n"}
+,{"stream_name":"stdout","time":454.702567559,"data":"Common Voice audio :\n"}
+,{"stream_name":"stdout","time":454.90345134,"data":"Competition data audio :  5831fd3d7134.mp3\n"}
+,{"stream_name":"stdout","time":455.111504631,"data":"--------------------------------------------------------------------------------\n"}
+,{"stream_name":"stdout","time":455.111528311,"data":"--------------------------------------------------------------------------------\n"}
+,{"stream_name":"stdout","time":455.111531851,"data":"Sentence :  এটি একটি গুরুত্বপূর্ণ রেল বিভাগের জন্য পরিচিত।\n"}
+,{"stream_name":"stdout","time":455.111535181,"data":"Common Voice audio :\n"}
+,{"stream_name":"stdout","time":455.135717701,"data":"Competition data audio :  ba8e9236358f.mp3\n"}
+,{"stream_name":"stdout","time":455.327957002,"data":"--------------------------------------------------------------------------------\n"}
+,{"stream_name":"stdout","time":455.328001362,"data":"--------------------------------------------------------------------------------\n"}
+,{"stream_name":"stdout","time":457.842483597,"data":"Sentence :  এটি সামগ্রিক পাঠক্রম, কোর্স, পরীক্ষা এবং ফলাফলগুলি নিয়ন্ত্রণ করে এবং অনুমোদন করে।\n"}
+,{"stream_name":"stdout","time":457.842531877,"data":"Common Voice audio :\n"}
+,{"stream_name":"stdout","time":458.040373948,"data":"Multiple audios in the competition dataset with the same sentence \n"}
+,{"stream_name":"stdout","time":458.040398808,"data":"\n"}
+,{"stream_name":"stdout","time":458.040401888,"data":"Competition data audio :  79660f8540b0.mp3\n"}
+,{"stream_name":"stdout","time":458.302004169,"data":"Competition data audio :  88db4447d274.mp3\n"}
+,{"stream_name":"stdout","time":458.532606861,"data":"Competition data audio :  ed34fbd6cf0b.mp3\n"}
+,{"stream_name":"stdout","time":458.770749963,"data":"--------------------------------------------------------------------------------\n"}
+,{"stream_name":"stdout","time":458.770780352,"data":"--------------------------------------------------------------------------------\n"}
+,{"stream_name":"stdout","time":464.378259715,"data":"Sentence :  তাদের একটি ছেলে এবং একটি মেয়ে আছে।\n"}
+,{"stream_name":"stdout","time":464.378324565,"data":"Common Voice audio :\n"}
+,{"stream_name":"stdout","time":464.576431276,"data":"Multiple audios in the competition dataset with the same sentence \n"}
+,{"stream_name":"stdout","time":464.576468386,"data":"\n"}
+,{"stream_name":"stdout","time":464.576498526,"data":"Competition data audio :  30e710e39566.mp3\n"}
+,{"stream_name":"stdout","time":464.811630637,"data":"Competition data audio :  b4c61f0f5afd.mp3\n"}
+,{"stream_name":"stdout","time":465.036936918,"data":"Competition data audio :  e4cc57dcf517.mp3\n"}
+,{"stream_name":"stdout","time":465.30257676,"data":"--------------------------------------------------------------------------------\n"}
+,{"stream_name":"stdout","time":465.30260857,"data":"--------------------------------------------------------------------------------\n"}
+,{"stream_name":"stdout","time":466.057549354,"data":"Sentence :  শীতল জলবায়ুতে কাণ্ডের বেশিরভাগ বৃদ্ধি বসন্ত এবং গ্রীষ্মের শুরুতে ঘটে।\n"}
+,{"stream_name":"stdout","time":466.057645774,"data":"Common Voice audio :\n"}
+,{"stream_name":"stdout","time":466.255401516,"data":"Multiple audios in the competition dataset with the same sentence \n"}
+,{"stream_name":"stdout","time":466.255426845,"data":"\n"}
+,{"stream_name":"stdout","time":466.255431045,"data":"Competition data audio :  113cd642691c.mp3\n"}
+,{"stream_name":"stdout","time":466.499374247,"data":"Competition data audio :  968e266863e8.mp3\n"}
+,{"stream_name":"stdout","time":466.720088108,"data":"Competition data audio :  b5764e70557d.mp3\n"}
+,{"stream_name":"stdout","time":467.01409308,"data":"--------------------------------------------------------------------------------\n"}
+,{"stream_name":"stdout","time":467.01413339,"data":"--------------------------------------------------------------------------------\n"}
+,{"stream_name":"stdout","time":468.061828886,"data":"Sentence :  ইউনিটটি বাংলাদেশে বৈজ্ঞানিক গবেষণা তহবিল গঠন করেছে।\n"}
+,{"stream_name":"stdout","time":468.061865106,"data":"Common Voice audio :\n"}
+,{"stream_name":"stdout","time":468.260425757,"data":"Multiple audios in the competition dataset with the same sentence \n"}
+,{"stream_name":"stdout","time":468.260479287,"data":"\n"}
+,{"stream_name":"stdout","time":468.260483737,"data":"Competition data audio :  30621db2115d.mp3\n"}
+,{"stream_name":"stdout","time":468.491173878,"data":"Competition data audio :  578726cb78a4.mp3\n"}
+,{"stream_name":"stdout","time":468.7056183,"data":"Competition data audio :  ec9f81af5c0a.mp3\n"}
+,{"stream_name":"stdout","time":468.71190234,"data":"--------------------------------------------------------------------------------\n"}
+,{"stream_name":"stdout","time":468.71194852,"data":"--------------------------------------------------------------------------------\n"}
+,{"stream_name":"stdout","time":471.298306515,"data":"Sentence :  বর্তমানে জমিদার বাড়ির ভৌত কাঠামো সংরক্ষণের অভাবে নষ্ট হয়ে যাচ্ছে।\n"}
+,{"stream_name":"stdout","time":471.298344275,"data":"Common Voice audio :\n"}
+,{"stream_name":"stdout","time":471.496049196,"data":"Multiple audios in the competition dataset with the same sentence \n"}
+,{"stream_name":"stdout","time":471.496102506,"data":"\n"}
+,{"stream_name":"stdout","time":471.496109866,"data":"Competition data audio :  17f4979f652e.mp3\n"}
+,{"stream_name":"stdout","time":471.730514617,"data":"Competition data audio :  87f243f631ea.mp3\n"}
+,{"stream_name":"stdout","time":471.959682938,"data":"Competition data audio :  90f45aad66a0.mp3\n"}
+,{"stream_name":"stdout","time":471.963997418,"data":"--------------------------------------------------------------------------------\n"}
+,{"stream_name":"stdout","time":471.964014048,"data":"--------------------------------------------------------------------------------\n"}
+,{"stream_name":"stdout","time":473.207362935,"data":"Audio in Common Voice dataset : \n"}
+,{"stream_name":"stderr","time":479.415976081,"data":"/opt/conda/lib/python3.10/site-packages/traitlets/traitlets.py:2930: FutureWarning: --Exporter.preprocessors=[\"remove_papermill_header.RemovePapermillHeader\"] for containers is deprecated in traitlets 5.0. You can pass `--Exporter.preprocessors item` ... multiple times to add items to a list.\n"}
+,{"stream_name":"stderr","time":479.416022431,"data":"  warn(\n"}
+,{"stream_name":"stderr","time":479.420470711,"data":"[NbConvertApp] WARNING | Config option `kernel_spec_manager_class` not recognized by `NbConvertApp`.\n"}
+,{"stream_name":"stderr","time":479.445263511,"data":"[NbConvertApp] Converting notebook __notebook__.ipynb to notebook\n"}
+,{"stream_name":"stderr","time":480.106029845,"data":"[NbConvertApp] Writing 9378981 bytes to __notebook__.ipynb\n"}
+,{"stream_name":"stderr","time":481.686893084,"data":"/opt/conda/lib/python3.10/site-packages/traitlets/traitlets.py:2930: FutureWarning: --Exporter.preprocessors=[\"nbconvert.preprocessors.ExtractOutputPreprocessor\"] for containers is deprecated in traitlets 5.0. You can pass `--Exporter.preprocessors item` ... multiple times to add items to a list.\n"}
+,{"stream_name":"stderr","time":481.687327044,"data":"  warn(\n"}
+,{"stream_name":"stderr","time":481.690677654,"data":"[NbConvertApp] WARNING | Config option `kernel_spec_manager_class` not recognized by `NbConvertApp`.\n"}
+,{"stream_name":"stderr","time":481.722324954,"data":"[NbConvertApp] Converting notebook __notebook__.ipynb to html\n"}
+,{"stream_name":"stderr","time":483.099897632,"data":"[NbConvertApp] Writing 9589984 bytes to __results__.html\n"}
+]

kaggle.json

@@ -0,0 +1 @@
+{"username":"nguynminhph","key":"cd06165eeba79f29a4db53f5d87eaf31"}

normalized.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06432a5dd7b5b27d38d9bbaebcd64aa85b79b85d0c4770ba66420bb63457fd24
+size 297143462

preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "Wav2Vec2Processor",
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

python-packages2.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c54f691d9a222bb3c61dc4db5574d209628f4e667be964cb8d50c1d7db11ef8f
+size 17653201

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f0960f05cdfd4480f2339a52034944ac99249181b2f20278a9b26ee3950c577
+size 3859313933

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd6572be7f0af6eabc0c935a13bbdbe6d745016ae2cdfc5b122b6a37750c92ac
+size 3963