Hugging Face's logo

EdoAbati
/
whisper-small-it

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Italian
whisper
whisper-event
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
EdoAbati commited on
Commit
7260b71
•
1 Parent(s): 9255450

End of training

Browse files
Files changed (3) hide show
  1. fine-tune-whisper-streaming.ipynb +68 -5
  2. pytorch_model.bin +1 -1
  3. runs/Dec07_20-55-49_155-248-246-251/events.out.tfevents.1670446586.155-248-246-251.72616.0 +2 -2
fine-tune-whisper-streaming.ipynb CHANGED
@@ -1064,8 +1064,8 @@
1064
  "\n",
1065
  " <div>\n",
1066
  " \n",
1067
- " <progress value='2001' max='5000' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
1068
- " [2001/5000 5:26:00 < 8:09:05, 0.10 it/s, Epoch 0.40/9223372036854775807]\n",
1069
  " </div>\n",
1070
  " <table border=\"1\" class=\"dataframe\">\n",
1071
  " <thead>\n",
@@ -1083,6 +1083,12 @@
1083
  " <td>0.257123</td>\n",
1084
  " <td>13.282745</td>\n",
1085
  " </tr>\n",
 
 
 
 
 
 
1086
  " </tbody>\n",
1087
  "</table><p>"
1088
  ],
@@ -1117,8 +1123,51 @@
1117
  " Num examples: Unknown\n",
1118
  " Batch size = 8\n",
1119
  "Reading metadata...: 15003it [00:00, 39593.28it/s]\n",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1120
  "The following columns in the evaluation set don't have a corresponding argument in `WhisperForConditionalGeneration.forward` and have been ignored: input_length. If input_length are not expected by `WhisperForConditionalGeneration.forward`, you can safely ignore this message.\n"
1121
  ]
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1122
  }
1123
  ],
1124
  "source": [
@@ -1147,7 +1196,7 @@
1147
  },
1148
  {
1149
  "cell_type": "code",
1150
- "execution_count": null,
1151
  "id": "6dd0e310-9b07-4133-ac14-2ed2d7524e22",
1152
  "metadata": {},
1153
  "outputs": [],
@@ -1173,10 +1222,24 @@
1173
  },
1174
  {
1175
  "cell_type": "code",
1176
- "execution_count": null,
1177
  "id": "95737cda-c5dd-4887-a4d0-dfcb0d61d977",
1178
  "metadata": {},
1179
- "outputs": [],
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1180
  "source": [
1181
  "trainer.push_to_hub(**kwargs)"
1182
  ]
 
1064
  "\n",
1065
  " <div>\n",
1066
  " \n",
1067
+ " <progress value='3001' max='5000' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
1068
+ " [3001/5000 8:52:48 < 5:55:08, 0.09 it/s, Epoch 1.12/9223372036854775807]\n",
1069
  " </div>\n",
1070
  " <table border=\"1\" class=\"dataframe\">\n",
1071
  " <thead>\n",
 
1083
  " <td>0.257123</td>\n",
1084
  " <td>13.282745</td>\n",
1085
  " </tr>\n",
1086
+ " <tr>\n",
1087
+ " <td>2000</td>\n",
1088
+ " <td>0.149400</td>\n",
1089
+ " <td>0.211123</td>\n",
1090
+ " <td>10.135153</td>\n",
1091
+ " </tr>\n",
1092
  " </tbody>\n",
1093
  "</table><p>"
1094
  ],
 
1123
  " Num examples: Unknown\n",
1124
  " Batch size = 8\n",
1125
  "Reading metadata...: 15003it [00:00, 39593.28it/s]\n",
1126
+ "The following columns in the evaluation set don't have a corresponding argument in `WhisperForConditionalGeneration.forward` and have been ignored: input_length. If input_length are not expected by `WhisperForConditionalGeneration.forward`, you can safely ignore this message.\n",
1127
+ "Saving model checkpoint to ./checkpoint-2000\n",
1128
+ "Configuration saved in ./checkpoint-2000/config.json\n",
1129
+ "Model weights saved in ./checkpoint-2000/pytorch_model.bin\n",
1130
+ "Feature extractor saved in ./checkpoint-2000/preprocessor_config.json\n",
1131
+ "tokenizer config file saved in ./checkpoint-2000/tokenizer_config.json\n",
1132
+ "Special tokens file saved in ./checkpoint-2000/special_tokens_map.json\n",
1133
+ "added tokens file saved in ./checkpoint-2000/added_tokens.json\n",
1134
+ "Feature extractor saved in ./preprocessor_config.json\n",
1135
+ "tokenizer config file saved in ./tokenizer_config.json\n",
1136
+ "Special tokens file saved in ./special_tokens_map.json\n",
1137
+ "added tokens file saved in ./added_tokens.json\n",
1138
+ "Reading metadata...: 152609it [00:04, 34307.28it/s]\n",
1139
+ "***** Running Evaluation *****\n",
1140
+ " Num examples: Unknown\n",
1141
+ " Batch size = 8\n",
1142
+ "Reading metadata...: 15003it [00:00, 38981.36it/s]\n",
1143
  "The following columns in the evaluation set don't have a corresponding argument in `WhisperForConditionalGeneration.forward` and have been ignored: input_length. If input_length are not expected by `WhisperForConditionalGeneration.forward`, you can safely ignore this message.\n"
1144
  ]
1145
+ },
1146
+ {
1147
+ "ename": "KeyboardInterrupt",
1148
+ "evalue": "",
1149
+ "output_type": "error",
1150
+ "traceback": [
1151
+ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
1152
+ "\u001b[0;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)",
1153
+ "Cell \u001b[0;32mIn[22], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m trainer\u001b[39m.\u001b[39;49mtrain()\n",
1154
+ "File \u001b[0;32m~/.env_hf/lib/python3.8/site-packages/transformers/trainer.py:1536\u001b[0m, in \u001b[0;36mTrainer.train\u001b[0;34m(self, resume_from_checkpoint, trial, ignore_keys_for_eval, **kwargs)\u001b[0m\n\u001b[1;32m 1531\u001b[0m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mmodel_wrapped \u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mmodel\n\u001b[1;32m 1533\u001b[0m inner_training_loop \u001b[39m=\u001b[39m find_executable_batch_size(\n\u001b[1;32m 1534\u001b[0m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_inner_training_loop, \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_train_batch_size, args\u001b[39m.\u001b[39mauto_find_batch_size\n\u001b[1;32m 1535\u001b[0m )\n\u001b[0;32m-> 1536\u001b[0m \u001b[39mreturn\u001b[39;00m inner_training_loop(\n\u001b[1;32m 1537\u001b[0m args\u001b[39m=\u001b[39;49margs,\n\u001b[1;32m 1538\u001b[0m resume_from_checkpoint\u001b[39m=\u001b[39;49mresume_from_checkpoint,\n\u001b[1;32m 1539\u001b[0m trial\u001b[39m=\u001b[39;49mtrial,\n\u001b[1;32m 1540\u001b[0m ignore_keys_for_eval\u001b[39m=\u001b[39;49mignore_keys_for_eval,\n\u001b[1;32m 1541\u001b[0m )\n",
1155
+ "File \u001b[0;32m~/.env_hf/lib/python3.8/site-packages/transformers/trainer.py:1861\u001b[0m, in \u001b[0;36mTrainer._inner_training_loop\u001b[0;34m(self, batch_size, args, resume_from_checkpoint, trial, ignore_keys_for_eval)\u001b[0m\n\u001b[1;32m 1858\u001b[0m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mstate\u001b[39m.\u001b[39mepoch \u001b[39m=\u001b[39m epoch \u001b[39m+\u001b[39m (step \u001b[39m+\u001b[39m \u001b[39m1\u001b[39m) \u001b[39m/\u001b[39m steps_in_epoch\n\u001b[1;32m 1859\u001b[0m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mcontrol \u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mcallback_handler\u001b[39m.\u001b[39mon_step_end(args, \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mstate, \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mcontrol)\n\u001b[0;32m-> 1861\u001b[0m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_maybe_log_save_evaluate(tr_loss, model, trial, epoch, ignore_keys_for_eval)\n\u001b[1;32m 1862\u001b[0m \u001b[39melse\u001b[39;00m:\n\u001b[1;32m 1863\u001b[0m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mcontrol \u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mcallback_handler\u001b[39m.\u001b[39mon_substep_end(args, \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mstate, \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mcontrol)\n",
1156
+ "File \u001b[0;32m~/.env_hf/lib/python3.8/site-packages/transformers/trainer.py:2124\u001b[0m, in \u001b[0;36mTrainer._maybe_log_save_evaluate\u001b[0;34m(self, tr_loss, model, trial, epoch, ignore_keys_for_eval)\u001b[0m\n\u001b[1;32m 2118\u001b[0m metrics \u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mevaluate(\n\u001b[1;32m 2119\u001b[0m eval_dataset\u001b[39m=\u001b[39meval_dataset,\n\u001b[1;32m 2120\u001b[0m ignore_keys\u001b[39m=\u001b[39mignore_keys_for_eval,\n\u001b[1;32m 2121\u001b[0m metric_key_prefix\u001b[39m=\u001b[39m\u001b[39mf\u001b[39m\u001b[39m\"\u001b[39m\u001b[39meval_\u001b[39m\u001b[39m{\u001b[39;00meval_dataset_name\u001b[39m}\u001b[39;00m\u001b[39m\"\u001b[39m,\n\u001b[1;32m 2122\u001b[0m )\n\u001b[1;32m 2123\u001b[0m \u001b[39melse\u001b[39;00m:\n\u001b[0;32m-> 2124\u001b[0m metrics \u001b[39m=\u001b[39m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mevaluate(ignore_keys\u001b[39m=\u001b[39;49mignore_keys_for_eval)\n\u001b[1;32m 2125\u001b[0m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_report_to_hp_search(trial, \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mstate\u001b[39m.\u001b[39mglobal_step, metrics)\n\u001b[1;32m 2127\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mcontrol\u001b[39m.\u001b[39mshould_save:\n",
1157
+ "File \u001b[0;32m~/.env_hf/lib/python3.8/site-packages/transformers/trainer_seq2seq.py:78\u001b[0m, in \u001b[0;36mSeq2SeqTrainer.evaluate\u001b[0;34m(self, eval_dataset, ignore_keys, metric_key_prefix, **gen_kwargs)\u001b[0m\n\u001b[1;32m 73\u001b[0m gen_kwargs[\u001b[39m\"\u001b[39m\u001b[39mnum_beams\u001b[39m\u001b[39m\"\u001b[39m] \u001b[39m=\u001b[39m (\n\u001b[1;32m 74\u001b[0m gen_kwargs[\u001b[39m\"\u001b[39m\u001b[39mnum_beams\u001b[39m\u001b[39m\"\u001b[39m] \u001b[39mif\u001b[39;00m gen_kwargs\u001b[39m.\u001b[39mget(\u001b[39m\"\u001b[39m\u001b[39mnum_beams\u001b[39m\u001b[39m\"\u001b[39m) \u001b[39mis\u001b[39;00m \u001b[39mnot\u001b[39;00m \u001b[39mNone\u001b[39;00m \u001b[39melse\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39margs\u001b[39m.\u001b[39mgeneration_num_beams\n\u001b[1;32m 75\u001b[0m )\n\u001b[1;32m 76\u001b[0m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_gen_kwargs \u001b[39m=\u001b[39m gen_kwargs\n\u001b[0;32m---> 78\u001b[0m \u001b[39mreturn\u001b[39;00m \u001b[39msuper\u001b[39;49m()\u001b[39m.\u001b[39;49mevaluate(eval_dataset, ignore_keys\u001b[39m=\u001b[39;49mignore_keys, metric_key_prefix\u001b[39m=\u001b[39;49mmetric_key_prefix)\n",
1158
+ "File \u001b[0;32m~/.env_hf/lib/python3.8/site-packages/transformers/trainer.py:2820\u001b[0m, in \u001b[0;36mTrainer.evaluate\u001b[0;34m(self, eval_dataset, ignore_keys, metric_key_prefix)\u001b[0m\n\u001b[1;32m 2817\u001b[0m start_time \u001b[39m=\u001b[39m time\u001b[39m.\u001b[39mtime()\n\u001b[1;32m 2819\u001b[0m eval_loop \u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mprediction_loop \u001b[39mif\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39margs\u001b[39m.\u001b[39muse_legacy_prediction_loop \u001b[39melse\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mevaluation_loop\n\u001b[0;32m-> 2820\u001b[0m output \u001b[39m=\u001b[39m eval_loop(\n\u001b[1;32m 2821\u001b[0m eval_dataloader,\n\u001b[1;32m 2822\u001b[0m description\u001b[39m=\u001b[39;49m\u001b[39m\"\u001b[39;49m\u001b[39mEvaluation\u001b[39;49m\u001b[39m\"\u001b[39;49m,\n\u001b[1;32m 2823\u001b[0m \u001b[39m# No point gathering the predictions if there are no metrics, otherwise we defer to\u001b[39;49;00m\n\u001b[1;32m 2824\u001b[0m \u001b[39m# self.args.prediction_loss_only\u001b[39;49;00m\n\u001b[1;32m 2825\u001b[0m prediction_loss_only\u001b[39m=\u001b[39;49m\u001b[39mTrue\u001b[39;49;00m \u001b[39mif\u001b[39;49;00m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mcompute_metrics \u001b[39mis\u001b[39;49;00m \u001b[39mNone\u001b[39;49;00m \u001b[39melse\u001b[39;49;00m \u001b[39mNone\u001b[39;49;00m,\n\u001b[1;32m 2826\u001b[0m ignore_keys\u001b[39m=\u001b[39;49mignore_keys,\n\u001b[1;32m 2827\u001b[0m metric_key_prefix\u001b[39m=\u001b[39;49mmetric_key_prefix,\n\u001b[1;32m 2828\u001b[0m )\n\u001b[1;32m 2830\u001b[0m total_batch_size \u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39margs\u001b[39m.\u001b[39meval_batch_size \u001b[39m*\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39margs\u001b[39m.\u001b[39mworld_size\n\u001b[1;32m 2831\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mf\u001b[39m\u001b[39m\"\u001b[39m\u001b[39m{\u001b[39;00mmetric_key_prefix\u001b[39m}\u001b[39;00m\u001b[39m_jit_compilation_time\u001b[39m\u001b[39m\"\u001b[39m \u001b[39min\u001b[39;00m output\u001b[39m.\u001b[39mmetrics:\n",
1159
+ "File \u001b[0;32m~/.env_hf/lib/python3.8/site-packages/transformers/trainer.py:3109\u001b[0m, in \u001b[0;36mTrainer.evaluation_loop\u001b[0;34m(self, dataloader, description, prediction_loss_only, ignore_keys, metric_key_prefix)\u001b[0m\n\u001b[1;32m 3105\u001b[0m metrics \u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mcompute_metrics(\n\u001b[1;32m 3106\u001b[0m EvalPrediction(predictions\u001b[39m=\u001b[39mall_preds, label_ids\u001b[39m=\u001b[39mall_labels, inputs\u001b[39m=\u001b[39mall_inputs)\n\u001b[1;32m 3107\u001b[0m )\n\u001b[1;32m 3108\u001b[0m \u001b[39melse\u001b[39;00m:\n\u001b[0;32m-> 3109\u001b[0m metrics \u001b[39m=\u001b[39m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mcompute_metrics(EvalPrediction(predictions\u001b[39m=\u001b[39;49mall_preds, label_ids\u001b[39m=\u001b[39;49mall_labels))\n\u001b[1;32m 3110\u001b[0m \u001b[39melse\u001b[39;00m:\n\u001b[1;32m 3111\u001b[0m metrics \u001b[39m=\u001b[39m {}\n",
1160
+ "Cell \u001b[0;32mIn[15], line 13\u001b[0m, in \u001b[0;36mcompute_metrics\u001b[0;34m(pred)\u001b[0m\n\u001b[1;32m 11\u001b[0m \u001b[39m# we do not want to group tokens when computing the metrics\u001b[39;00m\n\u001b[1;32m 12\u001b[0m pred_str \u001b[39m=\u001b[39m processor\u001b[39m.\u001b[39mtokenizer\u001b[39m.\u001b[39mbatch_decode(pred_ids, skip_special_tokens\u001b[39m=\u001b[39m\u001b[39mTrue\u001b[39;00m)\n\u001b[0;32m---> 13\u001b[0m label_str \u001b[39m=\u001b[39m processor\u001b[39m.\u001b[39;49mtokenizer\u001b[39m.\u001b[39;49mbatch_decode(label_ids, skip_special_tokens\u001b[39m=\u001b[39;49m\u001b[39mTrue\u001b[39;49;00m)\n\u001b[1;32m 15\u001b[0m \u001b[39mif\u001b[39;00m do_normalize_eval:\n\u001b[1;32m 16\u001b[0m pred_str \u001b[39m=\u001b[39m [normalizer(pred) \u001b[39mfor\u001b[39;00m pred \u001b[39min\u001b[39;00m pred_str]\n",
1161
+ "File \u001b[0;32m~/.env_hf/lib/python3.8/site-packages/transformers/tokenization_utils_base.py:3429\u001b[0m, in \u001b[0;36mPreTrainedTokenizerBase.batch_decode\u001b[0;34m(self, sequences, skip_special_tokens, clean_up_tokenization_spaces, **kwargs)\u001b[0m\n\u001b[1;32m 3406\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39mbatch_decode\u001b[39m(\n\u001b[1;32m 3407\u001b[0m \u001b[39mself\u001b[39m,\n\u001b[1;32m 3408\u001b[0m sequences: Union[List[\u001b[39mint\u001b[39m], List[List[\u001b[39mint\u001b[39m]], \u001b[39m\"\u001b[39m\u001b[39mnp.ndarray\u001b[39m\u001b[39m\"\u001b[39m, \u001b[39m\"\u001b[39m\u001b[39mtorch.Tensor\u001b[39m\u001b[39m\"\u001b[39m, \u001b[39m\"\u001b[39m\u001b[39mtf.Tensor\u001b[39m\u001b[39m\"\u001b[39m],\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 3411\u001b[0m \u001b[39m*\u001b[39m\u001b[39m*\u001b[39mkwargs\n\u001b[1;32m 3412\u001b[0m ) \u001b[39m-\u001b[39m\u001b[39m>\u001b[39m List[\u001b[39mstr\u001b[39m]:\n\u001b[1;32m 3413\u001b[0m \u001b[39m\"\"\"\u001b[39;00m\n\u001b[1;32m 3414\u001b[0m \u001b[39m Convert a list of lists of token ids into a list of strings by calling decode.\u001b[39;00m\n\u001b[1;32m 3415\u001b[0m \n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 3427\u001b[0m \u001b[39m `List[str]`: The list of decoded sentences.\u001b[39;00m\n\u001b[1;32m 3428\u001b[0m \u001b[39m \"\"\"\u001b[39;00m\n\u001b[0;32m-> 3429\u001b[0m \u001b[39mreturn\u001b[39;00m [\n\u001b[1;32m 3430\u001b[0m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mdecode(\n\u001b[1;32m 3431\u001b[0m seq,\n\u001b[1;32m 3432\u001b[0m skip_special_tokens\u001b[39m=\u001b[39mskip_special_tokens,\n\u001b[1;32m 3433\u001b[0m clean_up_tokenization_spaces\u001b[39m=\u001b[39mclean_up_tokenization_spaces,\n\u001b[1;32m 3434\u001b[0m \u001b[39m*\u001b[39m\u001b[39m*\u001b[39mkwargs,\n\u001b[1;32m 3435\u001b[0m )\n\u001b[1;32m 3436\u001b[0m \u001b[39mfor\u001b[39;00m seq \u001b[39min\u001b[39;00m sequences\n\u001b[1;32m 3437\u001b[0m ]\n",
1162
+ "File \u001b[0;32m~/.env_hf/lib/python3.8/site-packages/transformers/tokenization_utils_base.py:3430\u001b[0m, in \u001b[0;36m<listcomp>\u001b[0;34m(.0)\u001b[0m\n\u001b[1;32m 3406\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39mbatch_decode\u001b[39m(\n\u001b[1;32m 3407\u001b[0m \u001b[39mself\u001b[39m,\n\u001b[1;32m 3408\u001b[0m sequences: Union[List[\u001b[39mint\u001b[39m], List[List[\u001b[39mint\u001b[39m]], \u001b[39m\"\u001b[39m\u001b[39mnp.ndarray\u001b[39m\u001b[39m\"\u001b[39m, \u001b[39m\"\u001b[39m\u001b[39mtorch.Tensor\u001b[39m\u001b[39m\"\u001b[39m, \u001b[39m\"\u001b[39m\u001b[39mtf.Tensor\u001b[39m\u001b[39m\"\u001b[39m],\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 3411\u001b[0m \u001b[39m*\u001b[39m\u001b[39m*\u001b[39mkwargs\n\u001b[1;32m 3412\u001b[0m ) \u001b[39m-\u001b[39m\u001b[39m>\u001b[39m List[\u001b[39mstr\u001b[39m]:\n\u001b[1;32m 3413\u001b[0m \u001b[39m\"\"\"\u001b[39;00m\n\u001b[1;32m 3414\u001b[0m \u001b[39m Convert a list of lists of token ids into a list of strings by calling decode.\u001b[39;00m\n\u001b[1;32m 3415\u001b[0m \n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 3427\u001b[0m \u001b[39m `List[str]`: The list of decoded sentences.\u001b[39;00m\n\u001b[1;32m 3428\u001b[0m \u001b[39m \"\"\"\u001b[39;00m\n\u001b[1;32m 3429\u001b[0m \u001b[39mreturn\u001b[39;00m [\n\u001b[0;32m-> 3430\u001b[0m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mdecode(\n\u001b[1;32m 3431\u001b[0m seq,\n\u001b[1;32m 3432\u001b[0m skip_special_tokens\u001b[39m=\u001b[39;49mskip_special_tokens,\n\u001b[1;32m 3433\u001b[0m clean_up_tokenization_spaces\u001b[39m=\u001b[39;49mclean_up_tokenization_spaces,\n\u001b[1;32m 3434\u001b[0m \u001b[39m*\u001b[39;49m\u001b[39m*\u001b[39;49mkwargs,\n\u001b[1;32m 3435\u001b[0m )\n\u001b[1;32m 3436\u001b[0m \u001b[39mfor\u001b[39;00m seq \u001b[39min\u001b[39;00m sequences\n\u001b[1;32m 3437\u001b[0m ]\n",
1163
+ "File \u001b[0;32m~/.env_hf/lib/python3.8/site-packages/transformers/tokenization_utils_base.py:3468\u001b[0m, in \u001b[0;36mPreTrainedTokenizerBase.decode\u001b[0;34m(self, token_ids, skip_special_tokens, clean_up_tokenization_spaces, **kwargs)\u001b[0m\n\u001b[1;32m 3465\u001b[0m \u001b[39m# Convert inputs to python lists\u001b[39;00m\n\u001b[1;32m 3466\u001b[0m token_ids \u001b[39m=\u001b[39m to_py_obj(token_ids)\n\u001b[0;32m-> 3468\u001b[0m \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_decode(\n\u001b[1;32m 3469\u001b[0m token_ids\u001b[39m=\u001b[39;49mtoken_ids,\n\u001b[1;32m 3470\u001b[0m skip_special_tokens\u001b[39m=\u001b[39;49mskip_special_tokens,\n\u001b[1;32m 3471\u001b[0m clean_up_tokenization_spaces\u001b[39m=\u001b[39;49mclean_up_tokenization_spaces,\n\u001b[1;32m 3472\u001b[0m \u001b[39m*\u001b[39;49m\u001b[39m*\u001b[39;49mkwargs,\n\u001b[1;32m 3473\u001b[0m )\n",
1164
+ "File \u001b[0;32m~/.env_hf/lib/python3.8/site-packages/transformers/models/whisper/tokenization_whisper.py:496\u001b[0m, in \u001b[0;36mWhisperTokenizer._decode\u001b[0;34m(self, token_ids, skip_special_tokens, normalize, **kwargs)\u001b[0m\n\u001b[1;32m 491\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39m_decode\u001b[39m(\n\u001b[1;32m 492\u001b[0m \u001b[39mself\u001b[39m, token_ids: Union[\u001b[39mint\u001b[39m, List[\u001b[39mint\u001b[39m]], skip_special_tokens: \u001b[39mbool\u001b[39m \u001b[39m=\u001b[39m \u001b[39mFalse\u001b[39;00m, normalize: \u001b[39mbool\u001b[39m \u001b[39m=\u001b[39m \u001b[39mFalse\u001b[39;00m, \u001b[39m*\u001b[39m\u001b[39m*\u001b[39mkwargs\n\u001b[1;32m 493\u001b[0m ) \u001b[39m-\u001b[39m\u001b[39m>\u001b[39m \u001b[39mstr\u001b[39m:\n\u001b[1;32m 494\u001b[0m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_decode_use_source_tokenizer \u001b[39m=\u001b[39m kwargs\u001b[39m.\u001b[39mpop(\u001b[39m\"\u001b[39m\u001b[39muse_source_tokenizer\u001b[39m\u001b[39m\"\u001b[39m, \u001b[39mFalse\u001b[39;00m)\n\u001b[0;32m--> 496\u001b[0m filtered_tokens \u001b[39m=\u001b[39m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mconvert_ids_to_tokens(token_ids, skip_special_tokens\u001b[39m=\u001b[39;49mskip_special_tokens)\n\u001b[1;32m 498\u001b[0m \u001b[39m# To avoid mixing byte-level and unicode for byte-level BPT\u001b[39;00m\n\u001b[1;32m 499\u001b[0m \u001b[39m# we need to build string separately for added tokens and byte-level tokens\u001b[39;00m\n\u001b[1;32m 500\u001b[0m \u001b[39m# cf. https://github.com/huggingface/transformers/issues/1133\u001b[39;00m\n\u001b[1;32m 501\u001b[0m sub_texts \u001b[39m=\u001b[39m []\n",
1165
+ "File \u001b[0;32m~/.env_hf/lib/python3.8/site-packages/transformers/tokenization_utils.py:907\u001b[0m, in \u001b[0;36mPreTrainedTokenizer.convert_ids_to_tokens\u001b[0;34m(self, ids, skip_special_tokens)\u001b[0m\n\u001b[1;32m 905\u001b[0m \u001b[39mfor\u001b[39;00m index \u001b[39min\u001b[39;00m ids:\n\u001b[1;32m 906\u001b[0m index \u001b[39m=\u001b[39m \u001b[39mint\u001b[39m(index)\n\u001b[0;32m--> 907\u001b[0m \u001b[39mif\u001b[39;00m skip_special_tokens \u001b[39mand\u001b[39;00m index \u001b[39min\u001b[39;00m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mall_special_ids:\n\u001b[1;32m 908\u001b[0m \u001b[39mcontinue\u001b[39;00m\n\u001b[1;32m 909\u001b[0m \u001b[39mif\u001b[39;00m index \u001b[39min\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39madded_tokens_decoder:\n",
1166
+ "File \u001b[0;32m~/.env_hf/lib/python3.8/site-packages/transformers/tokenization_utils_base.py:1297\u001b[0m, in \u001b[0;36mSpecialTokensMixin.all_special_ids\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 1292\u001b[0m \u001b[39m@property\u001b[39m\n\u001b[1;32m 1293\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39mall_special_ids\u001b[39m(\u001b[39mself\u001b[39m) \u001b[39m-\u001b[39m\u001b[39m>\u001b[39m List[\u001b[39mint\u001b[39m]:\n\u001b[1;32m 1294\u001b[0m \u001b[39m\"\"\"\u001b[39;00m\n\u001b[1;32m 1295\u001b[0m \u001b[39m `List[int]`: List the ids of the special tokens(`'<unk>'`, `'<cls>'`, etc.) mapped to class attributes.\u001b[39;00m\n\u001b[1;32m 1296\u001b[0m \u001b[39m \"\"\"\u001b[39;00m\n\u001b[0;32m-> 1297\u001b[0m all_toks \u001b[39m=\u001b[39m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mall_special_tokens\n\u001b[1;32m 1298\u001b[0m all_ids \u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mconvert_tokens_to_ids(all_toks)\n\u001b[1;32m 1299\u001b[0m \u001b[39mreturn\u001b[39;00m all_ids\n",
1167
+ "File \u001b[0;32m~/.env_hf/lib/python3.8/site-packages/transformers/tokenization_utils_base.py:1273\u001b[0m, in \u001b[0;36mSpecialTokensMixin.all_special_tokens\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 1266\u001b[0m \u001b[39m@property\u001b[39m\n\u001b[1;32m 1267\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39mall_special_tokens\u001b[39m(\u001b[39mself\u001b[39m) \u001b[39m-\u001b[39m\u001b[39m>\u001b[39m List[\u001b[39mstr\u001b[39m]:\n\u001b[1;32m 1268\u001b[0m \u001b[39m\"\"\"\u001b[39;00m\n\u001b[1;32m 1269\u001b[0m \u001b[39m `List[str]`: All the special tokens (`'<unk>'`, `'<cls>'`, etc.) mapped to class attributes.\u001b[39;00m\n\u001b[1;32m 1270\u001b[0m \n\u001b[1;32m 1271\u001b[0m \u001b[39m Convert tokens of `tokenizers.AddedToken` type to string.\u001b[39;00m\n\u001b[1;32m 1272\u001b[0m \u001b[39m \"\"\"\u001b[39;00m\n\u001b[0;32m-> 1273\u001b[0m all_toks \u001b[39m=\u001b[39m [\u001b[39mstr\u001b[39m(s) \u001b[39mfor\u001b[39;00m s \u001b[39min\u001b[39;00m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mall_special_tokens_extended]\n\u001b[1;32m 1274\u001b[0m \u001b[39mreturn\u001b[39;00m all_toks\n",
1168
+ "File \u001b[0;32m~/.env_hf/lib/python3.8/site-packages/transformers/tokenization_utils_base.py:1289\u001b[0m, in \u001b[0;36mSpecialTokensMixin.all_special_tokens_extended\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 1287\u001b[0m \u001b[39mfor\u001b[39;00m attr_value \u001b[39min\u001b[39;00m set_attr\u001b[39m.\u001b[39mvalues():\n\u001b[1;32m 1288\u001b[0m all_toks \u001b[39m=\u001b[39m all_toks \u001b[39m+\u001b[39m (\u001b[39mlist\u001b[39m(attr_value) \u001b[39mif\u001b[39;00m \u001b[39misinstance\u001b[39m(attr_value, (\u001b[39mlist\u001b[39m, \u001b[39mtuple\u001b[39m)) \u001b[39melse\u001b[39;00m [attr_value])\n\u001b[0;32m-> 1289\u001b[0m all_toks \u001b[39m=\u001b[39m \u001b[39mlist\u001b[39;49m(OrderedDict\u001b[39m.\u001b[39;49mfromkeys(all_toks))\n\u001b[1;32m 1290\u001b[0m \u001b[39mreturn\u001b[39;00m all_toks\n",
1169
+ "\u001b[0;31mKeyboardInterrupt\u001b[0m: "
1170
+ ]
1171
  }
1172
  ],
1173
  "source": [
 
1196
  },
1197
  {
1198
  "cell_type": "code",
1199
+ "execution_count": 23,
1200
  "id": "6dd0e310-9b07-4133-ac14-2ed2d7524e22",
1201
  "metadata": {},
1202
  "outputs": [],
 
1222
  },
1223
  {
1224
  "cell_type": "code",
1225
+ "execution_count": 24,
1226
  "id": "95737cda-c5dd-4887-a4d0-dfcb0d61d977",
1227
  "metadata": {},
1228
+ "outputs": [
1229
+ {
1230
+ "name": "stderr",
1231
+ "output_type": "stream",
1232
+ "text": [
1233
+ "Saving model checkpoint to ./\n",
1234
+ "Configuration saved in ./config.json\n",
1235
+ "Model weights saved in ./pytorch_model.bin\n",
1236
+ "Feature extractor saved in ./preprocessor_config.json\n",
1237
+ "tokenizer config file saved in ./tokenizer_config.json\n",
1238
+ "Special tokens file saved in ./special_tokens_map.json\n",
1239
+ "added tokens file saved in ./added_tokens.json\n"
1240
+ ]
1241
+ }
1242
+ ],
1243
  "source": [
1244
  "trainer.push_to_hub(**kwargs)"
1245
  ]
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f465c3e382ff8be8e4d4feab9c434229e005b7a97f1b3bd3eed8e2fe14e4f1ce
3
  size 967102601
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09880c3705dc84c52d46720d1a6ffce4418604ee7989c7eecbb4a3c34bc8c158
3
  size 967102601
runs/Dec07_20-55-49_155-248-246-251/events.out.tfevents.1670446586.155-248-246-251.72616.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:36a1a6f6037cd72b359d90244183b18b4b6f46126bb96b2d0cda54e60f260ee8
3
- size 17380
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5abfc541666d8221aafea474e1db6a089b1ee261d20d55f07471693de7ec53ac
3
+ size 23660