Hugging Face's logo

JulioCastro
/
whisper-medium-ca

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Catalan
whisper
whisper-event
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
JulioCastro commited on
Commit
d5bf59f
•
1 Parent(s): 5f39e50

End of training

Browse files
Files changed (4) hide show
  1. .ipynb_checkpoints/trainv1-checkpoint.ipynb +0 -0
  2. pytorch_model.bin +1 -1
  3. runs/Dec17_13-19-25_129-146-107-233/events.out.tfevents.1671283218.129-146-107-233.68679.0 +2 -2
  4. trainv1.ipynb +81 -5
.ipynb_checkpoints/trainv1-checkpoint.ipynb CHANGED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b718545dfcde378778da6493b75f04950cb33aa9bb118521bb851b486f4958d8
3
  size 3055754841
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d095ca67c1c0f648934963373098877daa34d2cae27081ae9f2ef6afaaafe60
3
  size 3055754841
runs/Dec17_13-19-25_129-146-107-233/events.out.tfevents.1671283218.129-146-107-233.68679.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e40f5526e6ea93fe1b084bf145eb0d0c8a7597f29f047a201a056dd90f3f64a
3
- size 17473
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad4d309e8332806fbd0f6857c1da19ec2c5eae8f3a3c6a150ff61f868a71c79c
3
+ size 19357
trainv1.ipynb CHANGED
@@ -552,7 +552,7 @@
552
  },
553
  {
554
  "cell_type": "code",
555
- "execution_count": null,
556
  "id": "e4ce26c9-4737-4565-96b1-6da0d99ce084",
557
  "metadata": {},
558
  "outputs": [
@@ -580,8 +580,8 @@
580
  "\n",
581
  " <div>\n",
582
  " \n",
583
- " <progress value='2001' max='10000' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
584
- " [ 2001/10000 31:31:26 < 126:08:38, 0.02 it/s, Epoch 0.20/9223372036854775807]\n",
585
  " </div>\n",
586
  " <table border=\"1\" class=\"dataframe\">\n",
587
  " <thead>\n",
@@ -61945,6 +61945,60 @@
61945
  "Special tokens file saved in ./special_tokens_map.json\n",
61946
  "added tokens file saved in ./added_tokens.json\n"
61947
  ]
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
61948
  }
61949
  ],
61950
  "source": [
@@ -61953,7 +62007,7 @@
61953
  },
61954
  {
61955
  "cell_type": "code",
61956
- "execution_count": null,
61957
  "id": "606258de-cd15-43e4-8960-52ee02b9cab5",
61958
  "metadata": {},
61959
  "outputs": [],
@@ -61974,10 +62028,32 @@
61974
  "execution_count": null,
61975
  "id": "31305933-9906-4131-aa4e-6a6a53f4b7cb",
61976
  "metadata": {},
61977
- "outputs": [],
 
 
 
 
 
 
 
 
 
 
 
 
 
 
61978
  "source": [
61979
  "trainer.push_to_hub(**kwargs)"
61980
  ]
 
 
 
 
 
 
 
 
61981
  }
61982
  ],
61983
  "metadata": {
 
552
  },
553
  {
554
  "cell_type": "code",
555
+ "execution_count": 35,
556
  "id": "e4ce26c9-4737-4565-96b1-6da0d99ce084",
557
  "metadata": {},
558
  "outputs": [
 
580
  "\n",
581
  " <div>\n",
582
  " \n",
583
+ " <progress value='2321' max='10000' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
584
+ " [ 2321/10000 39:06:00 < 129:28:27, 0.02 it/s, Epoch 0.23/9223372036854775807]\n",
585
  " </div>\n",
586
  " <table border=\"1\" class=\"dataframe\">\n",
587
  " <thead>\n",
 
61945
  "Special tokens file saved in ./special_tokens_map.json\n",
61946
  "added tokens file saved in ./added_tokens.json\n"
61947
  ]
61948
+ },
61949
+ {
61950
+ "ename": "FileNotFoundError",
61951
+ "evalue": "https://openslr.org/resources/69/ca_es_female.zip",
61952
+ "output_type": "error",
61953
+ "traceback": [
61954
+ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
61955
+ "\u001b[0;31mServerDisconnectedError\u001b[0m Traceback (most recent call last)",
61956
+ "File \u001b[0;32m~/hf_env/lib/python3.8/site-packages/fsspec/implementations/http.py:407\u001b[0m, in \u001b[0;36mHTTPFileSystem._info\u001b[0;34m(self, url, **kwargs)\u001b[0m\n\u001b[1;32m 405\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m 406\u001b[0m info\u001b[38;5;241m.\u001b[39mupdate(\n\u001b[0;32m--> 407\u001b[0m \u001b[38;5;28;01mawait\u001b[39;00m _file_info(\n\u001b[1;32m 408\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mencode_url(url),\n\u001b[1;32m 409\u001b[0m size_policy\u001b[38;5;241m=\u001b[39mpolicy,\n\u001b[1;32m 410\u001b[0m session\u001b[38;5;241m=\u001b[39msession,\n\u001b[1;32m 411\u001b[0m \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mkwargs,\n\u001b[1;32m 412\u001b[0m \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs,\n\u001b[1;32m 413\u001b[0m )\n\u001b[1;32m 414\u001b[0m )\n\u001b[1;32m 415\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m info\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124msize\u001b[39m\u001b[38;5;124m\"\u001b[39m) \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n",
61957
+ "File \u001b[0;32m~/hf_env/lib/python3.8/site-packages/fsspec/implementations/http.py:788\u001b[0m, in \u001b[0;36m_file_info\u001b[0;34m(url, session, size_policy, **kwargs)\u001b[0m\n\u001b[1;32m 787\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m size_policy \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mget\u001b[39m\u001b[38;5;124m\"\u001b[39m:\n\u001b[0;32m--> 788\u001b[0m r \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mawait\u001b[39;00m session\u001b[38;5;241m.\u001b[39mget(url, allow_redirects\u001b[38;5;241m=\u001b[39mar, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m 789\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n",
61958
+ "File \u001b[0;32m~/hf_env/lib/python3.8/site-packages/aiohttp/client.py:560\u001b[0m, in \u001b[0;36mClientSession._request\u001b[0;34m(self, method, str_or_url, params, data, json, cookies, headers, skip_auto_headers, auth, allow_redirects, max_redirects, compress, chunked, expect100, raise_for_status, read_until_eof, proxy, proxy_auth, timeout, verify_ssl, fingerprint, ssl_context, ssl, proxy_headers, trace_request_ctx, read_bufsize)\u001b[0m\n\u001b[1;32m 559\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 560\u001b[0m \u001b[38;5;28;01mawait\u001b[39;00m resp\u001b[38;5;241m.\u001b[39mstart(conn)\n\u001b[1;32m 561\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mBaseException\u001b[39;00m:\n",
61959
+ "File \u001b[0;32m~/hf_env/lib/python3.8/site-packages/aiohttp/client_reqrep.py:899\u001b[0m, in \u001b[0;36mClientResponse.start\u001b[0;34m(self, connection)\u001b[0m\n\u001b[1;32m 898\u001b[0m protocol \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_protocol\n\u001b[0;32m--> 899\u001b[0m message, payload \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mawait\u001b[39;00m protocol\u001b[38;5;241m.\u001b[39mread() \u001b[38;5;66;03m# type: ignore[union-attr]\u001b[39;00m\n\u001b[1;32m 900\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m http\u001b[38;5;241m.\u001b[39mHttpProcessingError \u001b[38;5;28;01mas\u001b[39;00m exc:\n",
61960
+ "File \u001b[0;32m~/hf_env/lib/python3.8/site-packages/aiohttp/streams.py:616\u001b[0m, in \u001b[0;36mDataQueue.read\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 615\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 616\u001b[0m \u001b[38;5;28;01mawait\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_waiter\n\u001b[1;32m 617\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m (asyncio\u001b[38;5;241m.\u001b[39mCancelledError, asyncio\u001b[38;5;241m.\u001b[39mTimeoutError):\n",
61961
+ "\u001b[0;31mServerDisconnectedError\u001b[0m: Server disconnected",
61962
+ "\nThe above exception was the direct cause of the following exception:\n",
61963
+ "\u001b[0;31mFileNotFoundError\u001b[0m Traceback (most recent call last)",
61964
+ "Cell \u001b[0;32mIn[35], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mtrainer\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mtrain\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n",
61965
+ "File \u001b[0;32m~/hf_env/lib/python3.8/site-packages/transformers/trainer.py:1534\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 1529\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mmodel_wrapped \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mmodel\n\u001b[1;32m 1531\u001b[0m inner_training_loop \u001b[38;5;241m=\u001b[39m find_executable_batch_size(\n\u001b[1;32m 1532\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_inner_training_loop, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_train_batch_size, args\u001b[38;5;241m.\u001b[39mauto_find_batch_size\n\u001b[1;32m 1533\u001b[0m )\n\u001b[0;32m-> 1534\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43minner_training_loop\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 1535\u001b[0m \u001b[43m \u001b[49m\u001b[43margs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1536\u001b[0m \u001b[43m \u001b[49m\u001b[43mresume_from_checkpoint\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mresume_from_checkpoint\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1537\u001b[0m \u001b[43m \u001b[49m\u001b[43mtrial\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtrial\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1538\u001b[0m \u001b[43m \u001b[49m\u001b[43mignore_keys_for_eval\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mignore_keys_for_eval\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1539\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
61966
+ "File \u001b[0;32m~/hf_env/lib/python3.8/site-packages/transformers/trainer.py:1756\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 1753\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_load_rng_state(resume_from_checkpoint)\n\u001b[1;32m 1755\u001b[0m step \u001b[38;5;241m=\u001b[39m \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m\n\u001b[0;32m-> 1756\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m step, inputs \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28menumerate\u001b[39m(epoch_iterator):\n\u001b[1;32m 1757\u001b[0m \n\u001b[1;32m 1758\u001b[0m \u001b[38;5;66;03m# Skip past any already trained steps if resuming training\u001b[39;00m\n\u001b[1;32m 1759\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m steps_trained_in_current_epoch \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m0\u001b[39m:\n\u001b[1;32m 1760\u001b[0m steps_trained_in_current_epoch \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m=\u001b[39m \u001b[38;5;241m1\u001b[39m\n",
61967
+ "File \u001b[0;32m~/hf_env/lib/python3.8/site-packages/torch/utils/data/dataloader.py:628\u001b[0m, in \u001b[0;36m_BaseDataLoaderIter.__next__\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 625\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_sampler_iter \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m 626\u001b[0m \u001b[38;5;66;03m# TODO(https://github.com/pytorch/pytorch/issues/76750)\u001b[39;00m\n\u001b[1;32m 627\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_reset() \u001b[38;5;66;03m# type: ignore[call-arg]\u001b[39;00m\n\u001b[0;32m--> 628\u001b[0m data \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_next_data\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 629\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_num_yielded \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m \u001b[38;5;241m1\u001b[39m\n\u001b[1;32m 630\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_dataset_kind \u001b[38;5;241m==\u001b[39m _DatasetKind\u001b[38;5;241m.\u001b[39mIterable \u001b[38;5;129;01mand\u001b[39;00m \\\n\u001b[1;32m 631\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_IterableDataset_len_called \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;129;01mand\u001b[39;00m \\\n\u001b[1;32m 632\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_num_yielded \u001b[38;5;241m>\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_IterableDataset_len_called:\n",
61968
+ "File \u001b[0;32m~/hf_env/lib/python3.8/site-packages/torch/utils/data/dataloader.py:671\u001b[0m, in \u001b[0;36m_SingleProcessDataLoaderIter._next_data\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 669\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_next_data\u001b[39m(\u001b[38;5;28mself\u001b[39m):\n\u001b[1;32m 670\u001b[0m index \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_next_index() \u001b[38;5;66;03m# may raise StopIteration\u001b[39;00m\n\u001b[0;32m--> 671\u001b[0m data \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_dataset_fetcher\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfetch\u001b[49m\u001b[43m(\u001b[49m\u001b[43mindex\u001b[49m\u001b[43m)\u001b[49m \u001b[38;5;66;03m# may raise StopIteration\u001b[39;00m\n\u001b[1;32m 672\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_pin_memory:\n\u001b[1;32m 673\u001b[0m data \u001b[38;5;241m=\u001b[39m _utils\u001b[38;5;241m.\u001b[39mpin_memory\u001b[38;5;241m.\u001b[39mpin_memory(data, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_pin_memory_device)\n",
61969
+ "File \u001b[0;32m~/hf_env/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py:34\u001b[0m, in \u001b[0;36m_IterableDatasetFetcher.fetch\u001b[0;34m(self, possibly_batched_index)\u001b[0m\n\u001b[1;32m 32\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m _ \u001b[38;5;129;01min\u001b[39;00m possibly_batched_index:\n\u001b[1;32m 33\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m---> 34\u001b[0m data\u001b[38;5;241m.\u001b[39mappend(\u001b[38;5;28;43mnext\u001b[39;49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdataset_iter\u001b[49m\u001b[43m)\u001b[49m)\n\u001b[1;32m 35\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mStopIteration\u001b[39;00m:\n\u001b[1;32m 36\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mended \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mTrue\u001b[39;00m\n",
61970
+ "File \u001b[0;32m~/hf_env/lib/python3.8/site-packages/datasets/iterable_dataset.py:849\u001b[0m, in \u001b[0;36mIterableDataset.__iter__\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 846\u001b[0m \u001b[38;5;28;01myield from\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_iter_pytorch(worker_info)\n\u001b[1;32m 847\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m\n\u001b[0;32m--> 849\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m key, example \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_iter():\n\u001b[1;32m 850\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mfeatures:\n\u001b[1;32m 851\u001b[0m \u001b[38;5;66;03m# `IterableDataset` automatically fills missing columns with None.\u001b[39;00m\n\u001b[1;32m 852\u001b[0m \u001b[38;5;66;03m# This is done with `_apply_feature_types_on_example`.\u001b[39;00m\n\u001b[1;32m 853\u001b[0m \u001b[38;5;28;01myield\u001b[39;00m _apply_feature_types_on_example(\n\u001b[1;32m 854\u001b[0m example, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mfeatures, token_per_repo_id\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_token_per_repo_id\n\u001b[1;32m 855\u001b[0m )\n",
61971
+ "File \u001b[0;32m~/hf_env/lib/python3.8/site-packages/datasets/iterable_dataset.py:791\u001b[0m, in \u001b[0;36mIterableDataset._iter\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 789\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 790\u001b[0m ex_iterable \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_ex_iterable\n\u001b[0;32m--> 791\u001b[0m \u001b[38;5;28;01myield from\u001b[39;00m ex_iterable\n",
61972
+ "File \u001b[0;32m~/hf_env/lib/python3.8/site-packages/datasets/iterable_dataset.py:522\u001b[0m, in \u001b[0;36mFilteredExamplesIterable.__iter__\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 520\u001b[0m current_idx \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m batch_idx \u001b[38;5;241m+\u001b[39m \u001b[38;5;241m1\u001b[39m\n\u001b[1;32m 521\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m--> 522\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m key, example \u001b[38;5;129;01min\u001b[39;00m iterator:\n\u001b[1;32m 523\u001b[0m \u001b[38;5;66;03m# If not batched, we can apply the filtering function direcly\u001b[39;00m\n\u001b[1;32m 524\u001b[0m inputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mdict\u001b[39m(example)\n\u001b[1;32m 525\u001b[0m function_args \u001b[38;5;241m=\u001b[39m [inputs] \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39minput_columns \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;28;01melse\u001b[39;00m [inputs[col] \u001b[38;5;28;01mfor\u001b[39;00m col \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39minput_columns]\n",
61973
+ "File \u001b[0;32m~/hf_env/lib/python3.8/site-packages/datasets/iterable_dataset.py:577\u001b[0m, in \u001b[0;36mBufferShuffledExamplesIterable.__iter__\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 575\u001b[0m \u001b[38;5;66;03m# this is the shuffle buffer that we keep in memory\u001b[39;00m\n\u001b[1;32m 576\u001b[0m mem_buffer \u001b[38;5;241m=\u001b[39m []\n\u001b[0;32m--> 577\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m x \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mex_iterable:\n\u001b[1;32m 578\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(mem_buffer) \u001b[38;5;241m==\u001b[39m buffer_size: \u001b[38;5;66;03m# if the buffer is full, pick and example from it\u001b[39;00m\n\u001b[1;32m 579\u001b[0m i \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mnext\u001b[39m(indices_iterator)\n",
61974
+ "File \u001b[0;32m~/hf_env/lib/python3.8/site-packages/datasets/iterable_dataset.py:430\u001b[0m, in \u001b[0;36mMappedExamplesIterable.__iter__\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 428\u001b[0m current_idx \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m batch_idx \u001b[38;5;241m+\u001b[39m \u001b[38;5;241m1\u001b[39m\n\u001b[1;32m 429\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m--> 430\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m key, example \u001b[38;5;129;01min\u001b[39;00m iterator:\n\u001b[1;32m 431\u001b[0m \u001b[38;5;66;03m# If not batched, we can apply the transform and yield the example directly\u001b[39;00m\n\u001b[1;32m 432\u001b[0m \u001b[38;5;66;03m# first copy the example, since we might drop some keys\u001b[39;00m\n\u001b[1;32m 433\u001b[0m example \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mdict\u001b[39m(example)\n\u001b[1;32m 434\u001b[0m \u001b[38;5;66;03m# then apply the transform\u001b[39;00m\n",
61975
+ "File \u001b[0;32m~/hf_env/lib/python3.8/site-packages/datasets/iterable_dataset.py:687\u001b[0m, in \u001b[0;36mTypedExamplesIterable.__iter__\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 684\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m__iter__\u001b[39m(\u001b[38;5;28mself\u001b[39m):\n\u001b[1;32m 685\u001b[0m \u001b[38;5;66;03m# Then for each example, `TypedExamplesIterable` automatically fills missing columns with None.\u001b[39;00m\n\u001b[1;32m 686\u001b[0m \u001b[38;5;66;03m# This is done with `_apply_feature_types_on_example`.\u001b[39;00m\n\u001b[0;32m--> 687\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m key, example \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mex_iterable:\n\u001b[1;32m 688\u001b[0m \u001b[38;5;28;01myield\u001b[39;00m key, _apply_feature_types_on_example(\n\u001b[1;32m 689\u001b[0m example, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mfeatures, token_per_repo_id\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtoken_per_repo_id\n\u001b[1;32m 690\u001b[0m )\n",
61976
+ "File \u001b[0;32m~/hf_env/lib/python3.8/site-packages/datasets/iterable_dataset.py:175\u001b[0m, in \u001b[0;36mCyclingMultiSourcesExamplesIterable.__iter__\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 172\u001b[0m \u001b[38;5;28;01myield\u001b[39;00m \u001b[38;5;28mnext\u001b[39m(iterators[i])\n\u001b[1;32m 174\u001b[0m \u001b[38;5;66;03m# it will resume from the yield at the next call so that we can directly test if the iterable is exhausted and if we need to break out of the loop\u001b[39;00m\n\u001b[0;32m--> 175\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[43miterators\u001b[49m\u001b[43m[\u001b[49m\u001b[43mi\u001b[49m\u001b[43m]\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mhasnext\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m:\n\u001b[1;32m 176\u001b[0m is_exhausted[i] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mTrue\u001b[39;00m\n\u001b[1;32m 178\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mbool_strategy_func(is_exhausted):\n\u001b[1;32m 179\u001b[0m \u001b[38;5;66;03m# if the stopping criteria is met, break the main for loop\u001b[39;00m\n",
61977
+ "File \u001b[0;32m~/hf_env/lib/python3.8/site-packages/datasets/iterable_dataset.py:76\u001b[0m, in \u001b[0;36mHasNextIterator.hasnext\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 74\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_hasnext \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m 75\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m---> 76\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_thenext \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mnext\u001b[39;49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mit\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 77\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mStopIteration\u001b[39;00m:\n\u001b[1;32m 78\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_hasnext \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mFalse\u001b[39;00m\n",
61978
+ "File \u001b[0;32m~/hf_env/lib/python3.8/site-packages/datasets/iterable_dataset.py:430\u001b[0m, in \u001b[0;36mMappedExamplesIterable.__iter__\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 428\u001b[0m current_idx \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m batch_idx \u001b[38;5;241m+\u001b[39m \u001b[38;5;241m1\u001b[39m\n\u001b[1;32m 429\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m--> 430\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m key, example \u001b[38;5;129;01min\u001b[39;00m iterator:\n\u001b[1;32m 431\u001b[0m \u001b[38;5;66;03m# If not batched, we can apply the transform and yield the example directly\u001b[39;00m\n\u001b[1;32m 432\u001b[0m \u001b[38;5;66;03m# first copy the example, since we might drop some keys\u001b[39;00m\n\u001b[1;32m 433\u001b[0m example \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mdict\u001b[39m(example)\n\u001b[1;32m 434\u001b[0m \u001b[38;5;66;03m# then apply the transform\u001b[39;00m\n",
61979
+ "File \u001b[0;32m~/hf_env/lib/python3.8/site-packages/datasets/iterable_dataset.py:688\u001b[0m, in \u001b[0;36mTypedExamplesIterable.__iter__\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 684\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m__iter__\u001b[39m(\u001b[38;5;28mself\u001b[39m):\n\u001b[1;32m 685\u001b[0m \u001b[38;5;66;03m# Then for each example, `TypedExamplesIterable` automatically fills missing columns with None.\u001b[39;00m\n\u001b[1;32m 686\u001b[0m \u001b[38;5;66;03m# This is done with `_apply_feature_types_on_example`.\u001b[39;00m\n\u001b[1;32m 687\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m key, example \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mex_iterable:\n\u001b[0;32m--> 688\u001b[0m \u001b[38;5;28;01myield\u001b[39;00m key, \u001b[43m_apply_feature_types_on_example\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 689\u001b[0m \u001b[43m \u001b[49m\u001b[43mexample\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfeatures\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtoken_per_repo_id\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mtoken_per_repo_id\u001b[49m\n\u001b[1;32m 690\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n",
61980
+ "File \u001b[0;32m~/hf_env/lib/python3.8/site-packages/datasets/iterable_dataset.py:653\u001b[0m, in \u001b[0;36m_apply_feature_types_on_example\u001b[0;34m(example, features, token_per_repo_id)\u001b[0m\n\u001b[1;32m 651\u001b[0m encoded_example \u001b[38;5;241m=\u001b[39m features\u001b[38;5;241m.\u001b[39mencode_example(example)\n\u001b[1;32m 652\u001b[0m \u001b[38;5;66;03m# Decode example for Audio feature, e.g.\u001b[39;00m\n\u001b[0;32m--> 653\u001b[0m decoded_example \u001b[38;5;241m=\u001b[39m \u001b[43mfeatures\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdecode_example\u001b[49m\u001b[43m(\u001b[49m\u001b[43mencoded_example\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtoken_per_repo_id\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtoken_per_repo_id\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 654\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m decoded_example\n",
61981
+ "File \u001b[0;32m~/hf_env/lib/python3.8/site-packages/datasets/features/features.py:1835\u001b[0m, in \u001b[0;36mFeatures.decode_example\u001b[0;34m(self, example, token_per_repo_id)\u001b[0m\n\u001b[1;32m 1821\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mdecode_example\u001b[39m(\u001b[38;5;28mself\u001b[39m, example: \u001b[38;5;28mdict\u001b[39m, token_per_repo_id: Optional[Dict[\u001b[38;5;28mstr\u001b[39m, Union[\u001b[38;5;28mstr\u001b[39m, \u001b[38;5;28mbool\u001b[39m, \u001b[38;5;28;01mNone\u001b[39;00m]]] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m):\n\u001b[1;32m 1822\u001b[0m \u001b[38;5;124;03m\"\"\"Decode example with custom feature decoding.\u001b[39;00m\n\u001b[1;32m 1823\u001b[0m \n\u001b[1;32m 1824\u001b[0m \u001b[38;5;124;03m Args:\u001b[39;00m\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 1832\u001b[0m \u001b[38;5;124;03m `dict[str, Any]`\u001b[39;00m\n\u001b[1;32m 1833\u001b[0m \u001b[38;5;124;03m \"\"\"\u001b[39;00m\n\u001b[0;32m-> 1835\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m {\n\u001b[1;32m 1836\u001b[0m column_name: decode_nested_example(feature, value, token_per_repo_id\u001b[38;5;241m=\u001b[39mtoken_per_repo_id)\n\u001b[1;32m 1837\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_column_requires_decoding[column_name]\n\u001b[1;32m 1838\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m value\n\u001b[1;32m 1839\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m column_name, (feature, value) \u001b[38;5;129;01min\u001b[39;00m zip_dict(\n\u001b[1;32m 1840\u001b[0m {key: value \u001b[38;5;28;01mfor\u001b[39;00m key, value \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mitems() \u001b[38;5;28;01mif\u001b[39;00m key \u001b[38;5;129;01min\u001b[39;00m example}, example\n\u001b[1;32m 1841\u001b[0m )\n\u001b[1;32m 1842\u001b[0m }\n",
61982
+ "File \u001b[0;32m~/hf_env/lib/python3.8/site-packages/datasets/features/features.py:1836\u001b[0m, in \u001b[0;36m<dictcomp>\u001b[0;34m(.0)\u001b[0m\n\u001b[1;32m 1821\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mdecode_example\u001b[39m(\u001b[38;5;28mself\u001b[39m, example: \u001b[38;5;28mdict\u001b[39m, token_per_repo_id: Optional[Dict[\u001b[38;5;28mstr\u001b[39m, Union[\u001b[38;5;28mstr\u001b[39m, \u001b[38;5;28mbool\u001b[39m, \u001b[38;5;28;01mNone\u001b[39;00m]]] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m):\n\u001b[1;32m 1822\u001b[0m \u001b[38;5;124;03m\"\"\"Decode example with custom feature decoding.\u001b[39;00m\n\u001b[1;32m 1823\u001b[0m \n\u001b[1;32m 1824\u001b[0m \u001b[38;5;124;03m Args:\u001b[39;00m\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 1832\u001b[0m \u001b[38;5;124;03m `dict[str, Any]`\u001b[39;00m\n\u001b[1;32m 1833\u001b[0m \u001b[38;5;124;03m \"\"\"\u001b[39;00m\n\u001b[1;32m 1835\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m {\n\u001b[0;32m-> 1836\u001b[0m column_name: \u001b[43mdecode_nested_example\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfeature\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mvalue\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtoken_per_repo_id\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtoken_per_repo_id\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1837\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_column_requires_decoding[column_name]\n\u001b[1;32m 1838\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m value\n\u001b[1;32m 1839\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m column_name, (feature, value) \u001b[38;5;129;01min\u001b[39;00m zip_dict(\n\u001b[1;32m 1840\u001b[0m {key: value \u001b[38;5;28;01mfor\u001b[39;00m key, value \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mitems() \u001b[38;5;28;01mif\u001b[39;00m key \u001b[38;5;129;01min\u001b[39;00m example}, example\n\u001b[1;32m 1841\u001b[0m )\n\u001b[1;32m 1842\u001b[0m }\n",
61983
+ "File \u001b[0;32m~/hf_env/lib/python3.8/site-packages/datasets/features/features.py:1298\u001b[0m, in \u001b[0;36mdecode_nested_example\u001b[0;34m(schema, obj, token_per_repo_id)\u001b[0m\n\u001b[1;32m 1295\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(schema, (Audio, Image)):\n\u001b[1;32m 1296\u001b[0m \u001b[38;5;66;03m# we pass the token to read and decode files from private repositories in streaming mode\u001b[39;00m\n\u001b[1;32m 1297\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m obj \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;129;01mand\u001b[39;00m schema\u001b[38;5;241m.\u001b[39mdecode:\n\u001b[0;32m-> 1298\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mschema\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdecode_example\u001b[49m\u001b[43m(\u001b[49m\u001b[43mobj\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtoken_per_repo_id\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtoken_per_repo_id\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1299\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m obj\n",
61984
+ "File \u001b[0;32m~/hf_env/lib/python3.8/site-packages/datasets/features/audio.py:166\u001b[0m, in \u001b[0;36mAudio.decode_example\u001b[0;34m(self, value, token_per_repo_id)\u001b[0m\n\u001b[1;32m 164\u001b[0m array, sampling_rate \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_decode_non_mp3_file_like(file)\n\u001b[1;32m 165\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m--> 166\u001b[0m array, sampling_rate \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_decode_non_mp3_path_like\u001b[49m\u001b[43m(\u001b[49m\u001b[43mpath\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtoken_per_repo_id\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtoken_per_repo_id\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 167\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m {\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mpath\u001b[39m\u001b[38;5;124m\"\u001b[39m: path, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124marray\u001b[39m\u001b[38;5;124m\"\u001b[39m: array, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124msampling_rate\u001b[39m\u001b[38;5;124m\"\u001b[39m: sampling_rate}\n",
61985
+ "File \u001b[0;32m~/hf_env/lib/python3.8/site-packages/datasets/features/audio.py:270\u001b[0m, in \u001b[0;36mAudio._decode_non_mp3_path_like\u001b[0;34m(self, path, format, token_per_repo_id)\u001b[0m\n\u001b[1;32m 267\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m (\u001b[38;5;167;01mValueError\u001b[39;00m, \u001b[38;5;167;01mKeyError\u001b[39;00m):\n\u001b[1;32m 268\u001b[0m use_auth_token \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[0;32m--> 270\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m \u001b[43mxopen\u001b[49m\u001b[43m(\u001b[49m\u001b[43mpath\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mrb\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43muse_auth_token\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43muse_auth_token\u001b[49m\u001b[43m)\u001b[49m \u001b[38;5;28;01mas\u001b[39;00m f:\n\u001b[1;32m 271\u001b[0m array, sampling_rate \u001b[38;5;241m=\u001b[39m librosa\u001b[38;5;241m.\u001b[39mload(f, sr\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39msampling_rate, mono\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mmono)\n\u001b[1;32m 272\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m array, sampling_rate\n",
61986
+ "File \u001b[0;32m~/hf_env/lib/python3.8/site-packages/datasets/download/streaming_download_manager.py:458\u001b[0m, in \u001b[0;36mxopen\u001b[0;34m(file, mode, use_auth_token, *args, **kwargs)\u001b[0m\n\u001b[1;32m 456\u001b[0m kwargs \u001b[38;5;241m=\u001b[39m {\u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mnew_kwargs}\n\u001b[1;32m 457\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 458\u001b[0m file_obj \u001b[38;5;241m=\u001b[39m \u001b[43mfsspec\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mopen\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfile\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmode\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmode\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\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\u001b[38;5;241m.\u001b[39mopen()\n\u001b[1;32m 459\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m 460\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mstr\u001b[39m(e) \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mCannot seek streaming HTTP file\u001b[39m\u001b[38;5;124m\"\u001b[39m:\n",
61987
+ "File \u001b[0;32m~/hf_env/lib/python3.8/site-packages/fsspec/core.py:441\u001b[0m, in \u001b[0;36mopen\u001b[0;34m(urlpath, mode, compression, encoding, errors, protocol, newline, **kwargs)\u001b[0m\n\u001b[1;32m 391\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mopen\u001b[39m(\n\u001b[1;32m 392\u001b[0m urlpath,\n\u001b[1;32m 393\u001b[0m mode\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mrb\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 399\u001b[0m \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs,\n\u001b[1;32m 400\u001b[0m ):\n\u001b[1;32m 401\u001b[0m \u001b[38;5;124;03m\"\"\"Given a path or paths, return one ``OpenFile`` object.\u001b[39;00m\n\u001b[1;32m 402\u001b[0m \n\u001b[1;32m 403\u001b[0m \u001b[38;5;124;03m Parameters\u001b[39;00m\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 439\u001b[0m \u001b[38;5;124;03m ``OpenFile`` object.\u001b[39;00m\n\u001b[1;32m 440\u001b[0m \u001b[38;5;124;03m \"\"\"\u001b[39;00m\n\u001b[0;32m--> 441\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mopen_files\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 442\u001b[0m \u001b[43m \u001b[49m\u001b[43murlpath\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m[\u001b[49m\u001b[43murlpath\u001b[49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 443\u001b[0m \u001b[43m \u001b[49m\u001b[43mmode\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmode\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 444\u001b[0m \u001b[43m \u001b[49m\u001b[43mcompression\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcompression\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 445\u001b[0m \u001b[43m \u001b[49m\u001b[43mencoding\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mencoding\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 446\u001b[0m \u001b[43m \u001b[49m\u001b[43merrors\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43merrors\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 447\u001b[0m \u001b[43m \u001b[49m\u001b[43mprotocol\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mprotocol\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 448\u001b[0m \u001b[43m \u001b[49m\u001b[43mnewline\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mnewline\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 449\u001b[0m \u001b[43m \u001b[49m\u001b[43mexpand\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m 450\u001b[0m \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\u001b[1;32m 451\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m[\u001b[38;5;241m0\u001b[39m]\n",
61988
+ "File \u001b[0;32m~/hf_env/lib/python3.8/site-packages/fsspec/core.py:273\u001b[0m, in \u001b[0;36mopen_files\u001b[0;34m(urlpath, mode, compression, encoding, errors, name_function, num, protocol, newline, auto_mkdir, expand, **kwargs)\u001b[0m\n\u001b[1;32m 204\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mopen_files\u001b[39m(\n\u001b[1;32m 205\u001b[0m urlpath,\n\u001b[1;32m 206\u001b[0m mode\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mrb\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 216\u001b[0m \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs,\n\u001b[1;32m 217\u001b[0m ):\n\u001b[1;32m 218\u001b[0m \u001b[38;5;124;03m\"\"\"Given a path or paths, return a list of ``OpenFile`` objects.\u001b[39;00m\n\u001b[1;32m 219\u001b[0m \n\u001b[1;32m 220\u001b[0m \u001b[38;5;124;03m For writing, a str path must contain the \"*\" character, which will be filled\u001b[39;00m\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 271\u001b[0m \u001b[38;5;124;03m be used as a single context\u001b[39;00m\n\u001b[1;32m 272\u001b[0m \u001b[38;5;124;03m \"\"\"\u001b[39;00m\n\u001b[0;32m--> 273\u001b[0m fs, fs_token, paths \u001b[38;5;241m=\u001b[39m \u001b[43mget_fs_token_paths\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 274\u001b[0m \u001b[43m \u001b[49m\u001b[43murlpath\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 275\u001b[0m \u001b[43m \u001b[49m\u001b[43mmode\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 276\u001b[0m \u001b[43m \u001b[49m\u001b[43mnum\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mnum\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 277\u001b[0m \u001b[43m \u001b[49m\u001b[43mname_function\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mname_function\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 278\u001b[0m \u001b[43m \u001b[49m\u001b[43mstorage_options\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 279\u001b[0m \u001b[43m \u001b[49m\u001b[43mprotocol\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mprotocol\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 280\u001b[0m \u001b[43m \u001b[49m\u001b[43mexpand\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mexpand\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 281\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 282\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mr\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m mode \u001b[38;5;129;01mand\u001b[39;00m auto_mkdir:\n\u001b[1;32m 283\u001b[0m parents \u001b[38;5;241m=\u001b[39m {fs\u001b[38;5;241m.\u001b[39m_parent(path) \u001b[38;5;28;01mfor\u001b[39;00m path \u001b[38;5;129;01min\u001b[39;00m paths}\n",
61989
+ "File \u001b[0;32m~/hf_env/lib/python3.8/site-packages/fsspec/core.py:606\u001b[0m, in \u001b[0;36mget_fs_token_paths\u001b[0;34m(urlpath, mode, num, name_function, storage_options, protocol, expand)\u001b[0m\n\u001b[1;32m 604\u001b[0m inkwargs[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mfo\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m urls\n\u001b[1;32m 605\u001b[0m paths, protocol, _ \u001b[38;5;241m=\u001b[39m chain[\u001b[38;5;241m0\u001b[39m]\n\u001b[0;32m--> 606\u001b[0m fs \u001b[38;5;241m=\u001b[39m \u001b[43mfilesystem\u001b[49m\u001b[43m(\u001b[49m\u001b[43mprotocol\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43minkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 607\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(paths, (\u001b[38;5;28mlist\u001b[39m, \u001b[38;5;28mtuple\u001b[39m, \u001b[38;5;28mset\u001b[39m)):\n\u001b[1;32m 608\u001b[0m paths \u001b[38;5;241m=\u001b[39m [fs\u001b[38;5;241m.\u001b[39m_strip_protocol(u) \u001b[38;5;28;01mfor\u001b[39;00m u \u001b[38;5;129;01min\u001b[39;00m paths]\n",
61990
+ "File \u001b[0;32m~/hf_env/lib/python3.8/site-packages/fsspec/registry.py:284\u001b[0m, in \u001b[0;36mfilesystem\u001b[0;34m(protocol, **storage_options)\u001b[0m\n\u001b[1;32m 277\u001b[0m warnings\u001b[38;5;241m.\u001b[39mwarn(\n\u001b[1;32m 278\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mThe \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124marrow_hdfs\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m protocol has been deprecated and will be \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 279\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mremoved in the future. Specify it as \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mhdfs\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m.\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[1;32m 280\u001b[0m \u001b[38;5;167;01mDeprecationWarning\u001b[39;00m,\n\u001b[1;32m 281\u001b[0m )\n\u001b[1;32m 283\u001b[0m \u001b[38;5;28mcls\u001b[39m \u001b[38;5;241m=\u001b[39m get_filesystem_class(protocol)\n\u001b[0;32m--> 284\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mcls\u001b[39;49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mstorage_options\u001b[49m\u001b[43m)\u001b[49m\n",
61991
+ "File \u001b[0;32m~/hf_env/lib/python3.8/site-packages/fsspec/spec.py:76\u001b[0m, in \u001b[0;36m_Cached.__call__\u001b[0;34m(cls, *args, **kwargs)\u001b[0m\n\u001b[1;32m 74\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mcls\u001b[39m\u001b[38;5;241m.\u001b[39m_cache[token]\n\u001b[1;32m 75\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m---> 76\u001b[0m obj \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43msuper\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[38;5;21;43m__call__\u001b[39;49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\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\u001b[1;32m 77\u001b[0m \u001b[38;5;66;03m# Setting _fs_token here causes some static linters to complain.\u001b[39;00m\n\u001b[1;32m 78\u001b[0m obj\u001b[38;5;241m.\u001b[39m_fs_token_ \u001b[38;5;241m=\u001b[39m token\n",
61992
+ "File \u001b[0;32m~/hf_env/lib/python3.8/site-packages/fsspec/implementations/zip.py:53\u001b[0m, in \u001b[0;36mZipFileSystem.__init__\u001b[0;34m(self, fo, mode, target_protocol, target_options, block_size, **kwargs)\u001b[0m\n\u001b[1;32m 49\u001b[0m fo \u001b[38;5;241m=\u001b[39m fsspec\u001b[38;5;241m.\u001b[39mopen(\n\u001b[1;32m 50\u001b[0m fo, mode\u001b[38;5;241m=\u001b[39mmode \u001b[38;5;241m+\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mb\u001b[39m\u001b[38;5;124m\"\u001b[39m, protocol\u001b[38;5;241m=\u001b[39mtarget_protocol, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39m(target_options \u001b[38;5;129;01mor\u001b[39;00m {})\n\u001b[1;32m 51\u001b[0m )\n\u001b[1;32m 52\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mof \u001b[38;5;241m=\u001b[39m fo\n\u001b[0;32m---> 53\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mfo \u001b[38;5;241m=\u001b[39m \u001b[43mfo\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[38;5;21;43m__enter__\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m \u001b[38;5;66;03m# the whole instance is a context\u001b[39;00m\n\u001b[1;32m 54\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mzip \u001b[38;5;241m=\u001b[39m zipfile\u001b[38;5;241m.\u001b[39mZipFile(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mfo, mode\u001b[38;5;241m=\u001b[39mmode)\n\u001b[1;32m 55\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mblock_size \u001b[38;5;241m=\u001b[39m block_size\n",
61993
+ "File \u001b[0;32m~/hf_env/lib/python3.8/site-packages/fsspec/core.py:103\u001b[0m, in \u001b[0;36mOpenFile.__enter__\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 100\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m__enter__\u001b[39m(\u001b[38;5;28mself\u001b[39m):\n\u001b[1;32m 101\u001b[0m mode \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mmode\u001b[38;5;241m.\u001b[39mreplace(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mt\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m\"\u001b[39m)\u001b[38;5;241m.\u001b[39mreplace(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mb\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m\"\u001b[39m) \u001b[38;5;241m+\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mb\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m--> 103\u001b[0m f \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfs\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mopen\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mpath\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmode\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmode\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 105\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mfobjects \u001b[38;5;241m=\u001b[39m [f]\n\u001b[1;32m 107\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcompression \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n",
61994
+ "File \u001b[0;32m~/hf_env/lib/python3.8/site-packages/fsspec/spec.py:1106\u001b[0m, in \u001b[0;36mAbstractFileSystem.open\u001b[0;34m(self, path, mode, block_size, cache_options, compression, **kwargs)\u001b[0m\n\u001b[1;32m 1104\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 1105\u001b[0m ac \u001b[38;5;241m=\u001b[39m kwargs\u001b[38;5;241m.\u001b[39mpop(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mautocommit\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_intrans)\n\u001b[0;32m-> 1106\u001b[0m f \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_open\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 1107\u001b[0m \u001b[43m \u001b[49m\u001b[43mpath\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1108\u001b[0m \u001b[43m \u001b[49m\u001b[43mmode\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmode\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1109\u001b[0m \u001b[43m \u001b[49m\u001b[43mblock_size\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mblock_size\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1110\u001b[0m \u001b[43m \u001b[49m\u001b[43mautocommit\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mac\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1111\u001b[0m \u001b[43m \u001b[49m\u001b[43mcache_options\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcache_options\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1112\u001b[0m \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\u001b[1;32m 1113\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1114\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m compression \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m 1115\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mfsspec\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mcompression\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m compr\n",
61995
+ "File \u001b[0;32m~/hf_env/lib/python3.8/site-packages/fsspec/implementations/http.py:346\u001b[0m, in \u001b[0;36mHTTPFileSystem._open\u001b[0;34m(self, path, mode, block_size, autocommit, cache_type, cache_options, size, **kwargs)\u001b[0m\n\u001b[1;32m 344\u001b[0m kw[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124masynchronous\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39masynchronous\n\u001b[1;32m 345\u001b[0m kw\u001b[38;5;241m.\u001b[39mupdate(kwargs)\n\u001b[0;32m--> 346\u001b[0m size \u001b[38;5;241m=\u001b[39m size \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43minfo\u001b[49m\u001b[43m(\u001b[49m\u001b[43mpath\u001b[49m\u001b[43m,\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[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124msize\u001b[39m\u001b[38;5;124m\"\u001b[39m]\n\u001b[1;32m 347\u001b[0m session \u001b[38;5;241m=\u001b[39m sync(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mloop, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mset_session)\n\u001b[1;32m 348\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m block_size \u001b[38;5;129;01mand\u001b[39;00m size:\n",
61996
+ "File \u001b[0;32m~/hf_env/lib/python3.8/site-packages/fsspec/asyn.py:113\u001b[0m, in \u001b[0;36msync_wrapper.<locals>.wrapper\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 110\u001b[0m \u001b[38;5;129m@functools\u001b[39m\u001b[38;5;241m.\u001b[39mwraps(func)\n\u001b[1;32m 111\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mwrapper\u001b[39m(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs):\n\u001b[1;32m 112\u001b[0m \u001b[38;5;28mself\u001b[39m \u001b[38;5;241m=\u001b[39m obj \u001b[38;5;129;01mor\u001b[39;00m args[\u001b[38;5;241m0\u001b[39m]\n\u001b[0;32m--> 113\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43msync\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mloop\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mfunc\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\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",
61997
+ "File \u001b[0;32m~/hf_env/lib/python3.8/site-packages/fsspec/asyn.py:98\u001b[0m, in \u001b[0;36msync\u001b[0;34m(loop, func, timeout, *args, **kwargs)\u001b[0m\n\u001b[1;32m 96\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m FSTimeoutError \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mreturn_result\u001b[39;00m\n\u001b[1;32m 97\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(return_result, \u001b[38;5;167;01mBaseException\u001b[39;00m):\n\u001b[0;32m---> 98\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m return_result\n\u001b[1;32m 99\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 100\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m return_result\n",
61998
+ "File \u001b[0;32m~/hf_env/lib/python3.8/site-packages/fsspec/asyn.py:53\u001b[0m, in \u001b[0;36m_runner\u001b[0;34m(event, coro, result, timeout)\u001b[0m\n\u001b[1;32m 51\u001b[0m coro \u001b[38;5;241m=\u001b[39m asyncio\u001b[38;5;241m.\u001b[39mwait_for(coro, timeout\u001b[38;5;241m=\u001b[39mtimeout)\n\u001b[1;32m 52\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m---> 53\u001b[0m result[\u001b[38;5;241m0\u001b[39m] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mawait\u001b[39;00m coro\n\u001b[1;32m 54\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m ex:\n\u001b[1;32m 55\u001b[0m result[\u001b[38;5;241m0\u001b[39m] \u001b[38;5;241m=\u001b[39m ex\n",
61999
+ "File \u001b[0;32m~/hf_env/lib/python3.8/site-packages/fsspec/implementations/http.py:420\u001b[0m, in \u001b[0;36mHTTPFileSystem._info\u001b[0;34m(self, url, **kwargs)\u001b[0m\n\u001b[1;32m 417\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m exc:\n\u001b[1;32m 418\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m policy \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mget\u001b[39m\u001b[38;5;124m\"\u001b[39m:\n\u001b[1;32m 419\u001b[0m \u001b[38;5;66;03m# If get failed, then raise a FileNotFoundError\u001b[39;00m\n\u001b[0;32m--> 420\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mFileNotFoundError\u001b[39;00m(url) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mexc\u001b[39;00m\n\u001b[1;32m 421\u001b[0m logger\u001b[38;5;241m.\u001b[39mdebug(\u001b[38;5;28mstr\u001b[39m(exc))\n\u001b[1;32m 423\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m {\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mname\u001b[39m\u001b[38;5;124m\"\u001b[39m: url, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124msize\u001b[39m\u001b[38;5;124m\"\u001b[39m: \u001b[38;5;28;01mNone\u001b[39;00m, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39minfo, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtype\u001b[39m\u001b[38;5;124m\"\u001b[39m: \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mfile\u001b[39m\u001b[38;5;124m\"\u001b[39m}\n",
62000
+ "\u001b[0;31mFileNotFoundError\u001b[0m: https://openslr.org/resources/69/ca_es_female.zip"
62001
+ ]
62002
  }
62003
  ],
62004
  "source": [
 
62007
  },
62008
  {
62009
  "cell_type": "code",
62010
+ "execution_count": 36,
62011
  "id": "606258de-cd15-43e4-8960-52ee02b9cab5",
62012
  "metadata": {},
62013
  "outputs": [],
 
62028
  "execution_count": null,
62029
  "id": "31305933-9906-4131-aa4e-6a6a53f4b7cb",
62030
  "metadata": {},
62031
+ "outputs": [
62032
+ {
62033
+ "name": "stderr",
62034
+ "output_type": "stream",
62035
+ "text": [
62036
+ "Saving model checkpoint to ./\n",
62037
+ "Configuration saved in ./config.json\n",
62038
+ "Model weights saved in ./pytorch_model.bin\n",
62039
+ "Feature extractor saved in ./preprocessor_config.json\n",
62040
+ "tokenizer config file saved in ./tokenizer_config.json\n",
62041
+ "Special tokens file saved in ./special_tokens_map.json\n",
62042
+ "added tokens file saved in ./added_tokens.json\n"
62043
+ ]
62044
+ }
62045
+ ],
62046
  "source": [
62047
  "trainer.push_to_hub(**kwargs)"
62048
  ]
62049
+ },
62050
+ {
62051
+ "cell_type": "code",
62052
+ "execution_count": null,
62053
+ "id": "6b488a2a-3e81-4fbe-84a8-5cc7c59a5f92",
62054
+ "metadata": {},
62055
+ "outputs": [],
62056
+ "source": []
62057
  }
62058
  ],
62059
  "metadata": {