End of training

fine-tune-whisper-streaming.ipynb

@@ -1115,7 +1115,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 25,
    "id": "6dd0e310-9b07-4133-ac14-2ed2d7524e22",
    "metadata": {},
    "outputs": [],
@@ -1141,7 +1141,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 26,
    "id": "95737cda-c5dd-4887-a4d0-dfcb0d61d977",
    "metadata": {},
    "outputs": [
@@ -1155,32 +1155,20 @@
       "Feature extractor saved in ./preprocessor_config.json\n",
       "tokenizer config file saved in ./tokenizer_config.json\n",
       "Special tokens file saved in ./special_tokens_map.json\n",
-      "added tokens file saved in ./added_tokens.json\n"
+      "added tokens file saved in ./added_tokens.json\n",
+      "Several commits (7) will be pushed upstream.\n",
+      "The progress bars may be unreliable.\n"
      ]
     },
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "dc59052a3b7f45b2b896c03763c79f57",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Upload file pytorch_model.bin:   0%|          | 32.0k/922M [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "1c58442a44e84af9a6dff915e036de83",
+       "model_id": "e28b4896bb24431abb53886d20f8b826",
        "version_major": 2,
        "version_minor": 0
       },
       "text/plain": [
-       "Upload file training_args.bin: 100%|##########| 3.50k/3.50k [00:00<?, ?B/s]"
+       "Upload file runs/Dec10_02-58-52_129-213-89-27/events.out.tfevents.1670641248.129-213-89-27.128858.0:  87%|####…"
       ]
      },
      "metadata": {},
@@ -1192,11 +1180,6 @@
      "text": [
       "remote: Scanning LFS files for validity, may be slow...        \n",
       "remote: LFS file scan complete.        \n",
-      "To https://huggingface.co/kimbochen/whisper-small-zh-tw\n",
-      "   2ee4cf3..214645d  main -> main\n",
-      "\n",
-      "Dropping the following result as it does not have all the necessary fields:\n",
-      "{'task': {'name': 'Automatic Speech Recognition', 'type': 'automatic-speech-recognition'}, 'dataset': {'name': 'Common Voice 11.0', 'type': 'mozilla-foundation/common_voice_11_0', 'config': 'zh-TW', 'split': 'test', 'args': 'zh-TW'}}\n",
       "remote: ----------------------------------------------------------\u001b[0;31m        \n",
       "remote: Sorry, your push was rejected during YAML metadata verification:        \n",
       "remote: - Error: \"language[0]\" must only contain lowercase characters        \n",
@@ -1208,31 +1191,26 @@
       "To https://huggingface.co/kimbochen/whisper-small-zh-tw\n",
       " ! [remote rejected] main -> main (pre-receive hook declined)\n",
       "error: failed to push some refs to 'https://huggingface.co/kimbochen/whisper-small-zh-tw'\n",
-      "\n",
-      "Error pushing update to the model card. Please read logs and retry.\n",
-      "$remote: ----------------------------------------------------------\u001b[0;31m        \n",
-      "remote: Sorry, your push was rejected during YAML metadata verification:        \n",
-      "remote: - Error: \"language[0]\" must only contain lowercase characters        \n",
-      "remote: - Error: \"language[0]\" with value \"zh-TW\" is not valid. It must be an ISO 639-1, 639-2 or 639-3 code (two/three letters), or a special value like \"code\", \"multilingual\". If you want to use BCP-47 identifiers, you can specify them in language_bcp47.\u001b[0;32m        \n",
-      "remote: ----------------------------------------------------------        \n",
-      "remote: Please find the documentation at:        \n",
-      "remote: https://huggingface.co/docs/hub/model-cards#model-card-metadata\u001b[0;0m        \n",
-      "remote: ----------------------------------------------------------        \n",
-      "To https://huggingface.co/kimbochen/whisper-small-zh-tw\n",
-      " ! [remote rejected] main -> main (pre-receive hook declined)\n",
-      "error: failed to push some refs to 'https://huggingface.co/kimbochen/whisper-small-zh-tw'\n",
       "\n"
      ]
     },
     {
-     "data": {
-      "text/plain": [
-       "'https://huggingface.co/kimbochen/whisper-small-zh-tw/commit/214645d6cd1f0e7ab6a65a854eec2e349529961c'"
-      ]
-     },
-     "execution_count": 23,
-     "metadata": {},
-     "output_type": "execute_result"
+     "ename": "OSError",
+     "evalue": "remote: Scanning LFS files for validity, may be slow...        \nremote: LFS file scan complete.        \nremote: ----------------------------------------------------------\u001b[0;31m        \nremote: Sorry, your push was rejected during YAML metadata verification:        \nremote: - Error: \"language[0]\" must only contain lowercase characters        \nremote: - Error: \"language[0]\" with value \"zh-TW\" is not valid. It must be an ISO 639-1, 639-2 or 639-3 code (two/three letters), or a special value like \"code\", \"multilingual\". If you want to use BCP-47 identifiers, you can specify them in language_bcp47.\u001b[0;32m        \nremote: ----------------------------------------------------------        \nremote: Please find the documentation at:        \nremote: https://huggingface.co/docs/hub/model-cards#model-card-metadata\u001b[0;0m        \nremote: ----------------------------------------------------------        \nTo https://huggingface.co/kimbochen/whisper-small-zh-tw\n ! [remote rejected] main -> main (pre-receive hook declined)\nerror: failed to push some refs to 'https://huggingface.co/kimbochen/whisper-small-zh-tw'\n",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mCalledProcessError\u001b[0m                        Traceback (most recent call last)",
+      "File \u001b[0;32m~/.venv/lib/python3.8/site-packages/huggingface_hub/repository.py:1207\u001b[0m, in \u001b[0;36mRepository.git_push\u001b[0;34m(self, upstream, blocking, auto_lfs_prune)\u001b[0m\n\u001b[1;32m   1206\u001b[0m             \u001b[38;5;28;01mif\u001b[39;00m return_code:\n\u001b[0;32m-> 1207\u001b[0m                 \u001b[38;5;28;01mraise\u001b[39;00m subprocess\u001b[38;5;241m.\u001b[39mCalledProcessError(\n\u001b[1;32m   1208\u001b[0m                     return_code, process\u001b[38;5;241m.\u001b[39margs, output\u001b[38;5;241m=\u001b[39mstdout, stderr\u001b[38;5;241m=\u001b[39mstderr\n\u001b[1;32m   1209\u001b[0m                 )\n\u001b[1;32m   1211\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m subprocess\u001b[38;5;241m.\u001b[39mCalledProcessError \u001b[38;5;28;01mas\u001b[39;00m exc:\n",
+      "\u001b[0;31mCalledProcessError\u001b[0m: Command '['git', 'push', '--set-upstream', 'origin', 'main']' returned non-zero exit status 1.",
+      "\nDuring handling of the above exception, another exception occurred:\n",
+      "\u001b[0;31mOSError\u001b[0m                                   Traceback (most recent call last)",
+      "Cell \u001b[0;32mIn[26], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mtrainer\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mpush_to_hub\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[0;32m~/.venv/lib/python3.8/site-packages/transformers/trainer.py:3492\u001b[0m, in \u001b[0;36mTrainer.push_to_hub\u001b[0;34m(self, commit_message, blocking, **kwargs)\u001b[0m\n\u001b[1;32m   3489\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mpush_in_progress\u001b[38;5;241m.\u001b[39m_process\u001b[38;5;241m.\u001b[39mkill()\n\u001b[1;32m   3490\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mpush_in_progress \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[0;32m-> 3492\u001b[0m git_head_commit_url \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrepo\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mpush_to_hub\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   3493\u001b[0m \u001b[43m    \u001b[49m\u001b[43mcommit_message\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcommit_message\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mblocking\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mblocking\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mauto_lfs_prune\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mTrue\u001b[39;49;00m\n\u001b[1;32m   3494\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   3495\u001b[0m \u001b[38;5;66;03m# push separately the model card to be independant from the rest of the model\u001b[39;00m\n\u001b[1;32m   3496\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39margs\u001b[38;5;241m.\u001b[39mshould_save:\n",
+      "File \u001b[0;32m~/.venv/lib/python3.8/site-packages/huggingface_hub/repository.py:1432\u001b[0m, in \u001b[0;36mRepository.push_to_hub\u001b[0;34m(self, commit_message, blocking, clean_ok, auto_lfs_prune)\u001b[0m\n\u001b[1;32m   1430\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mgit_add(auto_lfs_track\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m)\n\u001b[1;32m   1431\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mgit_commit(commit_message)\n\u001b[0;32m-> 1432\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mgit_push\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   1433\u001b[0m \u001b[43m    \u001b[49m\u001b[43mupstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43mf\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43morigin \u001b[39;49m\u001b[38;5;132;43;01m{\u001b[39;49;00m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcurrent_branch\u001b[49m\u001b[38;5;132;43;01m}\u001b[39;49;00m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1434\u001b[0m \u001b[43m    \u001b[49m\u001b[43mblocking\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mblocking\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1435\u001b[0m \u001b[43m    \u001b[49m\u001b[43mauto_lfs_prune\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mauto_lfs_prune\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1436\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[0;32m~/.venv/lib/python3.8/site-packages/huggingface_hub/repository.py:1212\u001b[0m, in \u001b[0;36mRepository.git_push\u001b[0;34m(self, upstream, blocking, auto_lfs_prune)\u001b[0m\n\u001b[1;32m   1207\u001b[0m                 \u001b[38;5;28;01mraise\u001b[39;00m subprocess\u001b[38;5;241m.\u001b[39mCalledProcessError(\n\u001b[1;32m   1208\u001b[0m                     return_code, process\u001b[38;5;241m.\u001b[39margs, output\u001b[38;5;241m=\u001b[39mstdout, stderr\u001b[38;5;241m=\u001b[39mstderr\n\u001b[1;32m   1209\u001b[0m                 )\n\u001b[1;32m   1211\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m subprocess\u001b[38;5;241m.\u001b[39mCalledProcessError \u001b[38;5;28;01mas\u001b[39;00m exc:\n\u001b[0;32m-> 1212\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mEnvironmentError\u001b[39;00m(exc\u001b[38;5;241m.\u001b[39mstderr)\n\u001b[1;32m   1214\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m blocking:\n\u001b[1;32m   1216\u001b[0m     \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mstatus_method\u001b[39m():\n",
+      "\u001b[0;31mOSError\u001b[0m: remote: Scanning LFS files for validity, may be slow...        \nremote: LFS file scan complete.        \nremote: ----------------------------------------------------------\u001b[0;31m        \nremote: Sorry, your push was rejected during YAML metadata verification:        \nremote: - Error: \"language[0]\" must only contain lowercase characters        \nremote: - Error: \"language[0]\" with value \"zh-TW\" is not valid. It must be an ISO 639-1, 639-2 or 639-3 code (two/three letters), or a special value like \"code\", \"multilingual\". If you want to use BCP-47 identifiers, you can specify them in language_bcp47.\u001b[0;32m        \nremote: ----------------------------------------------------------        \nremote: Please find the documentation at:        \nremote: https://huggingface.co/docs/hub/model-cards#model-card-metadata\u001b[0;0m        \nremote: ----------------------------------------------------------        \nTo https://huggingface.co/kimbochen/whisper-small-zh-tw\n ! [remote rejected] main -> main (pre-receive hook declined)\nerror: failed to push some refs to 'https://huggingface.co/kimbochen/whisper-small-zh-tw'\n"
+     ]
     }
    ],
    "source": [