emilios commited on
Commit
aec1f79
1 Parent(s): 0fcacdf

notebook e5 updated

Browse files
Files changed (1) hide show
  1. e5_interleaving-cl.ipynb +518 -145
e5_interleaving-cl.ipynb CHANGED
@@ -125,20 +125,20 @@
125
  "Requirement already satisfied: torch in ./.local/lib/python3.8/site-packages (1.13.0)\n",
126
  "Requirement already satisfied: torchaudio in ./.local/lib/python3.8/site-packages (0.13.0)\n",
127
  "Requirement already satisfied: torchvision in ./.local/lib/python3.8/site-packages (0.14.0)\n",
128
- "Requirement already satisfied: nvidia-cuda-runtime-cu11==11.7.99 in ./.local/lib/python3.8/site-packages (from torch) (11.7.99)\n",
129
- "Requirement already satisfied: nvidia-cudnn-cu11==8.5.0.96 in ./.local/lib/python3.8/site-packages (from torch) (8.5.0.96)\n",
130
  "Requirement already satisfied: nvidia-cublas-cu11==11.10.3.66 in ./.local/lib/python3.8/site-packages (from torch) (11.10.3.66)\n",
131
- "Requirement already satisfied: typing-extensions in ./.local/lib/python3.8/site-packages (from torch) (4.4.0)\n",
132
  "Requirement already satisfied: nvidia-cuda-nvrtc-cu11==11.7.99 in ./.local/lib/python3.8/site-packages (from torch) (11.7.99)\n",
 
 
 
133
  "Requirement already satisfied: wheel in /usr/lib/python3/dist-packages (from nvidia-cublas-cu11==11.10.3.66->torch) (0.34.2)\n",
134
  "Requirement already satisfied: setuptools in /usr/lib/python3/dist-packages (from nvidia-cublas-cu11==11.10.3.66->torch) (45.2.0)\n",
135
- "Requirement already satisfied: pillow!=8.3.*,>=5.3.0 in /usr/lib/python3/dist-packages (from torchvision) (7.0.0)\n",
136
  "Requirement already satisfied: requests in ./.local/lib/python3.8/site-packages (from torchvision) (2.28.1)\n",
 
137
  "Requirement already satisfied: numpy in ./.local/lib/python3.8/site-packages (from torchvision) (1.23.5)\n",
138
  "Requirement already satisfied: certifi>=2017.4.17 in /usr/lib/python3/dist-packages (from requests->torchvision) (2019.11.28)\n",
139
  "Requirement already satisfied: charset-normalizer<3,>=2 in ./.local/lib/python3.8/site-packages (from requests->torchvision) (2.1.1)\n",
140
- "Requirement already satisfied: urllib3<1.27,>=1.21.1 in ./.local/lib/python3.8/site-packages (from requests->torchvision) (1.26.13)\n",
141
- "Requirement already satisfied: idna<4,>=2.5 in /usr/lib/python3/dist-packages (from requests->torchvision) (2.8)\n"
142
  ]
143
  }
144
  ],
@@ -200,7 +200,7 @@
200
  "name": "stdout",
201
  "output_type": "stream",
202
  "text": [
203
- "Tue Dec 13 21:26:01 2022 \n",
204
  "+-----------------------------------------------------------------------------+\n",
205
  "| NVIDIA-SMI 515.65.01 Driver Version: 515.65.01 CUDA Version: 11.7 |\n",
206
  "|-------------------------------+----------------------+----------------------+\n",
@@ -209,7 +209,7 @@
209
  "| | | MIG M. |\n",
210
  "|===============================+======================+======================|\n",
211
  "| 0 NVIDIA A100-SXM... On | 00000000:06:00.0 Off | 0 |\n",
212
- "| N/A 41C P0 50W / 400W | 0MiB / 40960MiB | 0% Default |\n",
213
  "| | | Disabled |\n",
214
  "+-------------------------------+----------------------+----------------------+\n",
215
  " \n",
@@ -261,39 +261,37 @@
261
  "output_type": "stream",
262
  "text": [
263
  "Get:1 https://nvidia.github.io/libnvidia-container/stable/ubuntu18.04/amd64 InRelease [1484 B]\n",
264
- "Hit:2 https://nvidia.github.io/nvidia-container-runtime/stable/ubuntu18.04/amd64 InRelease\n",
265
- "Get:3 https://packages.cloud.google.com/apt cloud-sdk InRelease [6751 B] \n",
266
- "Hit:4 http://archive.lambdalabs.com/ubuntu focal InRelease \n",
267
- "Hit:5 https://download.docker.com/linux/ubuntu focal InRelease \n",
268
- "Hit:6 https://packages.microsoft.com/repos/azure-cli focal InRelease \n",
269
- "Hit:7 http://archive.ubuntu.com/ubuntu focal InRelease \n",
270
- "Get:8 http://security.ubuntu.com/ubuntu focal-security InRelease [114 kB] \n",
271
- "Ign:9 http://ppa.launchpad.net/jonathonf/ffmpeg-4/ubuntu focal InRelease \n",
272
- "Get:10 http://archive.ubuntu.com/ubuntu focal-updates InRelease [114 kB] \n",
273
- "Hit:11 https://pkg.cloudflare.com/cloudflared focal InRelease \n",
274
  "Err:12 http://ppa.launchpad.net/jonathonf/ffmpeg-4/ubuntu focal Release \n",
275
  " 404 Not Found [IP: 185.125.190.52 80]\n",
276
  "Hit:13 https://ppa.launchpadcontent.net/deadsnakes/ppa/ubuntu focal InRelease \n",
277
- "Get:14 http://archive.ubuntu.com/ubuntu focal-backports InRelease [108 kB] \n",
278
- "Get:15 http://archive.ubuntu.com/ubuntu focal-updates/main amd64 Packages [2269 kB]\n",
279
- "Get:16 http://archive.ubuntu.com/ubuntu focal-updates/universe amd64 Packages [1009 kB]\n",
280
- "Reading package lists... Done \n",
281
  "E: The repository 'http://ppa.launchpad.net/jonathonf/ffmpeg-4/ubuntu focal Release' does not have a Release file.\n",
282
  "N: Updating from such a repository can't be done securely, and is therefore disabled by default.\n",
283
  "N: See apt-secure(8) manpage for repository creation and user configuration details.\n",
284
- "Get:1 https://nvidia.github.io/libnvidia-container/stable/ubuntu18.04/amd64 InRelease [1484 B]\n",
285
- "Hit:2 https://nvidia.github.io/nvidia-container-runtime/stable/ubuntu18.04/amd64 InRelease\n",
286
- "Hit:3 https://packages.cloud.google.com/apt cloud-sdk InRelease \u001b[0m\u001b[33m\n",
287
- "Hit:4 http://archive.lambdalabs.com/ubuntu focal InRelease \u001b[0m\n",
288
- "Hit:5 https://download.docker.com/linux/ubuntu focal InRelease \u001b[0m\n",
289
- "Ign:6 http://ppa.launchpad.net/jonathonf/ffmpeg-4/ubuntu focal InRelease \u001b[0m\u001b[33m\u001b[33m\u001b[33m\n",
290
- "Hit:7 http://archive.ubuntu.com/ubuntu focal InRelease \u001b[0m\n",
291
- "Hit:8 https://packages.microsoft.com/repos/azure-cli focal InRelease \u001b[0m\n",
292
- "Hit:9 http://security.ubuntu.com/ubuntu focal-security InRelease \u001b[0m\n",
293
- "Hit:10 https://pkg.cloudflare.com/cloudflared focal InRelease \u001b[0m\u001b[33m\u001b[33m\n",
294
  "Hit:11 http://archive.ubuntu.com/ubuntu focal-updates InRelease \u001b[0m\n",
295
- "Hit:12 http://archive.ubuntu.com/ubuntu focal-backports InRelease \u001b[0m \u001b[0m\u001b[33m\u001b[33m\u001b[33m\n",
296
- "Err:13 http://ppa.launchpad.net/jonathonf/ffmpeg-4/ubuntu focal Release\n",
297
  " 404 Not Found [IP: 185.125.190.52 80]\n",
298
  "Hit:14 https://ppa.launchpadcontent.net/deadsnakes/ppa/ubuntu focal InRelease\n",
299
  "Reading package lists... Done\u001b[33m\u001b[33m\n",
@@ -347,150 +345,164 @@
347
  "text": [
348
  "Defaulting to user installation because normal site-packages is not writeable\n",
349
  "Collecting git+https://github.com/huggingface/datasets\n",
350
- " Cloning https://github.com/huggingface/datasets to /tmp/pip-req-build-ju8bkpld\n",
351
- " Running command git clone --filter=blob:none --quiet https://github.com/huggingface/datasets /tmp/pip-req-build-ju8bkpld\n",
352
  " Resolved https://github.com/huggingface/datasets to commit c902456677116a081f762fa2b4aad13a0aa04d6e\n",
353
  " Installing build dependencies ... \u001b[?25ldone\n",
354
  "\u001b[?25h Getting requirements to build wheel ... \u001b[?25ldone\n",
355
  "\u001b[?25h Preparing metadata (pyproject.toml) ... \u001b[?25ldone\n",
356
- "\u001b[?25hRequirement already satisfied: dill<0.3.7 in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (0.3.6)\n",
357
- "Requirement already satisfied: requests>=2.19.0 in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (2.28.1)\n",
358
- "Requirement already satisfied: numpy>=1.17 in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (1.23.5)\n",
 
 
359
  "Requirement already satisfied: aiohttp in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (3.8.3)\n",
360
- "Requirement already satisfied: packaging in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (22.0)\n",
361
- "Requirement already satisfied: xxhash in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (3.1.0)\n",
362
  "Requirement already satisfied: pyarrow>=6.0.0 in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (10.0.1)\n",
 
363
  "Requirement already satisfied: responses<0.19 in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (0.18.0)\n",
364
- "Requirement already satisfied: multiprocess in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (0.70.14)\n",
365
- "Requirement already satisfied: fsspec[http]>=2021.11.1 in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (2022.11.0)\n",
 
366
  "Requirement already satisfied: pandas in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (1.5.1)\n",
367
  "Requirement already satisfied: tqdm>=4.62.1 in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (4.64.1)\n",
368
- "Requirement already satisfied: pyyaml>=5.1 in /usr/lib/python3/dist-packages (from datasets==2.7.1.dev0) (5.3.1)\n",
369
- "Requirement already satisfied: huggingface-hub<1.0.0,>=0.2.0 in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (0.11.1)\n",
370
  "Requirement already satisfied: yarl<2.0,>=1.0 in ./.local/lib/python3.8/site-packages (from aiohttp->datasets==2.7.1.dev0) (1.8.2)\n",
 
 
371
  "Requirement already satisfied: aiosignal>=1.1.2 in ./.local/lib/python3.8/site-packages (from aiohttp->datasets==2.7.1.dev0) (1.3.1)\n",
 
372
  "Requirement already satisfied: multidict<7.0,>=4.5 in ./.local/lib/python3.8/site-packages (from aiohttp->datasets==2.7.1.dev0) (6.0.3)\n",
373
  "Requirement already satisfied: attrs>=17.3.0 in /usr/lib/python3/dist-packages (from aiohttp->datasets==2.7.1.dev0) (19.3.0)\n",
374
- "Requirement already satisfied: async-timeout<5.0,>=4.0.0a3 in ./.local/lib/python3.8/site-packages (from aiohttp->datasets==2.7.1.dev0) (4.0.2)\n",
375
- "Requirement already satisfied: charset-normalizer<3.0,>=2.0 in ./.local/lib/python3.8/site-packages (from aiohttp->datasets==2.7.1.dev0) (2.1.1)\n",
376
- "Requirement already satisfied: frozenlist>=1.1.1 in ./.local/lib/python3.8/site-packages (from aiohttp->datasets==2.7.1.dev0) (1.3.3)\n",
377
  "Requirement already satisfied: filelock in /usr/lib/python3/dist-packages (from huggingface-hub<1.0.0,>=0.2.0->datasets==2.7.1.dev0) (3.0.12)\n",
378
  "Requirement already satisfied: typing-extensions>=3.7.4.3 in ./.local/lib/python3.8/site-packages (from huggingface-hub<1.0.0,>=0.2.0->datasets==2.7.1.dev0) (4.4.0)\n",
379
- "Requirement already satisfied: certifi>=2017.4.17 in /usr/lib/python3/dist-packages (from requests>=2.19.0->datasets==2.7.1.dev0) (2019.11.28)\n",
380
  "Requirement already satisfied: urllib3<1.27,>=1.21.1 in ./.local/lib/python3.8/site-packages (from requests>=2.19.0->datasets==2.7.1.dev0) (1.26.13)\n",
381
  "Requirement already satisfied: idna<4,>=2.5 in /usr/lib/python3/dist-packages (from requests>=2.19.0->datasets==2.7.1.dev0) (2.8)\n",
382
- "Requirement already satisfied: python-dateutil>=2.8.1 in ./.local/lib/python3.8/site-packages (from pandas->datasets==2.7.1.dev0) (2.8.2)\n",
383
  "Requirement already satisfied: pytz>=2020.1 in ./.local/lib/python3.8/site-packages (from pandas->datasets==2.7.1.dev0) (2022.5)\n",
 
384
  "Requirement already satisfied: six>=1.5 in /usr/lib/python3/dist-packages (from python-dateutil>=2.8.1->pandas->datasets==2.7.1.dev0) (1.14.0)\n",
385
  "Defaulting to user installation because normal site-packages is not writeable\n",
386
  "Collecting git+https://github.com/huggingface/transformers\n",
387
- " Cloning https://github.com/huggingface/transformers to /tmp/pip-req-build-9scgt3ru\n",
388
- " Running command git clone --filter=blob:none --quiet https://github.com/huggingface/transformers /tmp/pip-req-build-9scgt3ru\n",
389
  " Resolved https://github.com/huggingface/transformers to commit d994473b05a83ea398d9f10ca458855df095e22d\n",
390
  " Installing build dependencies ... \u001b[?25ldone\n",
391
  "\u001b[?25h Getting requirements to build wheel ... \u001b[?25ldone\n",
392
  "\u001b[?25h Preparing metadata (pyproject.toml) ... \u001b[?25ldone\n",
393
- "\u001b[?25hRequirement already satisfied: tokenizers!=0.11.3,<0.14,>=0.11.1 in ./.local/lib/python3.8/site-packages (from transformers==4.26.0.dev0) (0.13.2)\n",
394
- "Requirement already satisfied: huggingface-hub<1.0,>=0.10.0 in ./.local/lib/python3.8/site-packages (from transformers==4.26.0.dev0) (0.11.1)\n",
395
- "Requirement already satisfied: packaging>=20.0 in ./.local/lib/python3.8/site-packages (from transformers==4.26.0.dev0) (22.0)\n",
396
- "Requirement already satisfied: numpy>=1.17 in ./.local/lib/python3.8/site-packages (from transformers==4.26.0.dev0) (1.23.5)\n",
397
- "Requirement already satisfied: filelock in /usr/lib/python3/dist-packages (from transformers==4.26.0.dev0) (3.0.12)\n",
398
  "Requirement already satisfied: pyyaml>=5.1 in /usr/lib/python3/dist-packages (from transformers==4.26.0.dev0) (5.3.1)\n",
399
  "Requirement already satisfied: requests in ./.local/lib/python3.8/site-packages (from transformers==4.26.0.dev0) (2.28.1)\n",
 
 
 
 
 
400
  "Requirement already satisfied: regex!=2019.12.17 in ./.local/lib/python3.8/site-packages (from transformers==4.26.0.dev0) (2022.10.31)\n",
401
- "Requirement already satisfied: tqdm>=4.27 in ./.local/lib/python3.8/site-packages (from transformers==4.26.0.dev0) (4.64.1)\n",
402
  "Requirement already satisfied: typing-extensions>=3.7.4.3 in ./.local/lib/python3.8/site-packages (from huggingface-hub<1.0,>=0.10.0->transformers==4.26.0.dev0) (4.4.0)\n",
403
- "Requirement already satisfied: charset-normalizer<3,>=2 in ./.local/lib/python3.8/site-packages (from requests->transformers==4.26.0.dev0) (2.1.1)\n",
404
  "Requirement already satisfied: idna<4,>=2.5 in /usr/lib/python3/dist-packages (from requests->transformers==4.26.0.dev0) (2.8)\n",
405
- "Requirement already satisfied: certifi>=2017.4.17 in /usr/lib/python3/dist-packages (from requests->transformers==4.26.0.dev0) (2019.11.28)\n",
406
  "Requirement already satisfied: urllib3<1.27,>=1.21.1 in ./.local/lib/python3.8/site-packages (from requests->transformers==4.26.0.dev0) (1.26.13)\n",
 
 
407
  "Defaulting to user installation because normal site-packages is not writeable\n",
408
  "Requirement already satisfied: librosa in ./.local/lib/python3.8/site-packages (0.9.2)\n",
409
- "Requirement already satisfied: scikit-learn>=0.19.1 in /usr/lib/python3/dist-packages (from librosa) (0.22.2.post1)\n",
410
- "Requirement already satisfied: joblib>=0.14 in ./.local/lib/python3.8/site-packages (from librosa) (1.2.0)\n",
411
- "Requirement already satisfied: soundfile>=0.10.2 in ./.local/lib/python3.8/site-packages (from librosa) (0.11.0)\n",
412
  "Requirement already satisfied: numpy>=1.17.0 in ./.local/lib/python3.8/site-packages (from librosa) (1.23.5)\n",
413
- "Requirement already satisfied: pooch>=1.0 in ./.local/lib/python3.8/site-packages (from librosa) (1.6.0)\n",
414
- "Requirement already satisfied: decorator>=4.0.10 in /usr/lib/python3/dist-packages (from librosa) (4.4.2)\n",
415
  "Requirement already satisfied: audioread>=2.1.9 in ./.local/lib/python3.8/site-packages (from librosa) (3.0.0)\n",
416
- "Requirement already satisfied: numba>=0.45.1 in ./.local/lib/python3.8/site-packages (from librosa) (0.56.4)\n",
417
- "Requirement already satisfied: scipy>=1.2.0 in ./.local/lib/python3.8/site-packages (from librosa) (1.9.3)\n",
418
  "Requirement already satisfied: packaging>=20.0 in ./.local/lib/python3.8/site-packages (from librosa) (22.0)\n",
419
  "Requirement already satisfied: resampy>=0.2.2 in ./.local/lib/python3.8/site-packages (from librosa) (0.4.2)\n",
420
- "Requirement already satisfied: setuptools in /usr/lib/python3/dist-packages (from numba>=0.45.1->librosa) (45.2.0)\n",
 
 
 
421
  "Requirement already satisfied: llvmlite<0.40,>=0.39.0dev0 in ./.local/lib/python3.8/site-packages (from numba>=0.45.1->librosa) (0.39.1)\n",
422
  "Requirement already satisfied: importlib-metadata in ./.local/lib/python3.8/site-packages (from numba>=0.45.1->librosa) (5.0.0)\n",
423
- "Requirement already satisfied: requests>=2.19.0 in ./.local/lib/python3.8/site-packages (from pooch>=1.0->librosa) (2.28.1)\n",
424
  "Requirement already satisfied: appdirs>=1.3.0 in /usr/lib/python3/dist-packages (from pooch>=1.0->librosa) (1.4.3)\n",
 
425
  "Requirement already satisfied: cffi>=1.0 in /usr/lib/python3/dist-packages (from soundfile>=0.10.2->librosa) (1.14.0)\n",
426
- "Requirement already satisfied: certifi>=2017.4.17 in /usr/lib/python3/dist-packages (from requests>=2.19.0->pooch>=1.0->librosa) (2019.11.28)\n",
427
- "Requirement already satisfied: idna<4,>=2.5 in /usr/lib/python3/dist-packages (from requests>=2.19.0->pooch>=1.0->librosa) (2.8)\n",
428
  "Requirement already satisfied: charset-normalizer<3,>=2 in ./.local/lib/python3.8/site-packages (from requests>=2.19.0->pooch>=1.0->librosa) (2.1.1)\n",
 
 
429
  "Requirement already satisfied: urllib3<1.27,>=1.21.1 in ./.local/lib/python3.8/site-packages (from requests>=2.19.0->pooch>=1.0->librosa) (1.26.13)\n",
430
  "Requirement already satisfied: zipp>=0.5 in /usr/lib/python3/dist-packages (from importlib-metadata->numba>=0.45.1->librosa) (1.0.0)\n",
431
  "Defaulting to user installation because normal site-packages is not writeable\n",
432
- "Requirement already satisfied: jiwer in ./.local/lib/python3.8/site-packages (2.5.1)\n",
433
- "Requirement already satisfied: levenshtein==0.20.2 in ./.local/lib/python3.8/site-packages (from jiwer) (0.20.2)\n",
434
- "Requirement already satisfied: rapidfuzz<3.0.0,>=2.3.0 in ./.local/lib/python3.8/site-packages (from levenshtein==0.20.2->jiwer) (2.13.6)\n",
435
- "Defaulting to user installation because normal site-packages is not writeable\n",
436
  "Requirement already satisfied: gradio in ./.local/lib/python3.8/site-packages (3.13.0)\n",
437
- "Requirement already satisfied: pyyaml in /usr/lib/python3/dist-packages (from gradio) (5.3.1)\n",
438
- "Requirement already satisfied: aiohttp in ./.local/lib/python3.8/site-packages (from gradio) (3.8.3)\n",
439
- "Requirement already satisfied: pandas in ./.local/lib/python3.8/site-packages (from gradio) (1.5.1)\n",
440
- "Requirement already satisfied: pydub in ./.local/lib/python3.8/site-packages (from gradio) (0.25.1)\n",
441
- "Requirement already satisfied: websockets>=10.0 in ./.local/lib/python3.8/site-packages (from gradio) (10.4)\n",
442
- "Requirement already satisfied: httpx in ./.local/lib/python3.8/site-packages (from gradio) (0.23.1)\n",
443
  "Requirement already satisfied: pillow in /usr/lib/python3/dist-packages (from gradio) (7.0.0)\n",
444
- "Requirement already satisfied: uvicorn in ./.local/lib/python3.8/site-packages (from gradio) (0.20.0)\n",
445
- "Requirement already satisfied: paramiko in ./.local/lib/python3.8/site-packages (from gradio) (2.12.0)\n",
446
- "Requirement already satisfied: numpy in ./.local/lib/python3.8/site-packages (from gradio) (1.23.5)\n",
447
- "Requirement already satisfied: h11<0.13,>=0.11 in ./.local/lib/python3.8/site-packages (from gradio) (0.12.0)\n",
448
- "Requirement already satisfied: requests in ./.local/lib/python3.8/site-packages (from gradio) (2.28.1)\n",
449
- "Requirement already satisfied: fsspec in ./.local/lib/python3.8/site-packages (from gradio) (2022.11.0)\n",
450
- "Requirement already satisfied: orjson in ./.local/lib/python3.8/site-packages (from gradio) (3.8.3)\n",
451
- "Requirement already satisfied: python-multipart in ./.local/lib/python3.8/site-packages (from gradio) (0.0.5)\n",
452
  "Requirement already satisfied: pydantic in ./.local/lib/python3.8/site-packages (from gradio) (1.10.2)\n",
453
- "Requirement already satisfied: markdown-it-py[linkify,plugins] in ./.local/lib/python3.8/site-packages (from gradio) (2.1.0)\n",
454
  "Requirement already satisfied: ffmpy in ./.local/lib/python3.8/site-packages (from gradio) (0.3.0)\n",
 
455
  "Requirement already satisfied: fastapi in ./.local/lib/python3.8/site-packages (from gradio) (0.88.0)\n",
 
 
 
 
 
 
 
 
 
456
  "Requirement already satisfied: jinja2 in ./.local/lib/python3.8/site-packages (from gradio) (3.1.2)\n",
 
457
  "Requirement already satisfied: matplotlib in ./.local/lib/python3.8/site-packages (from gradio) (3.5.3)\n",
458
- "Requirement already satisfied: pycryptodome in ./.local/lib/python3.8/site-packages (from gradio) (3.16.0)\n",
459
- "Requirement already satisfied: aiosignal>=1.1.2 in ./.local/lib/python3.8/site-packages (from aiohttp->gradio) (1.3.1)\n",
 
 
 
460
  "Requirement already satisfied: multidict<7.0,>=4.5 in ./.local/lib/python3.8/site-packages (from aiohttp->gradio) (6.0.3)\n",
461
- "Requirement already satisfied: frozenlist>=1.1.1 in ./.local/lib/python3.8/site-packages (from aiohttp->gradio) (1.3.3)\n",
462
  "Requirement already satisfied: attrs>=17.3.0 in /usr/lib/python3/dist-packages (from aiohttp->gradio) (19.3.0)\n",
463
- "Requirement already satisfied: async-timeout<5.0,>=4.0.0a3 in ./.local/lib/python3.8/site-packages (from aiohttp->gradio) (4.0.2)\n",
464
- "Requirement already satisfied: charset-normalizer<3.0,>=2.0 in ./.local/lib/python3.8/site-packages (from aiohttp->gradio) (2.1.1)\n",
465
  "Requirement already satisfied: yarl<2.0,>=1.0 in ./.local/lib/python3.8/site-packages (from aiohttp->gradio) (1.8.2)\n",
 
 
 
466
  "Requirement already satisfied: starlette==0.22.0 in ./.local/lib/python3.8/site-packages (from fastapi->gradio) (0.22.0)\n",
467
- "Requirement already satisfied: typing-extensions>=3.10.0 in ./.local/lib/python3.8/site-packages (from starlette==0.22.0->fastapi->gradio) (4.4.0)\n",
468
  "Requirement already satisfied: anyio<5,>=3.4.0 in ./.local/lib/python3.8/site-packages (from starlette==0.22.0->fastapi->gradio) (3.6.2)\n",
469
- "Requirement already satisfied: rfc3986[idna2008]<2,>=1.3 in ./.local/lib/python3.8/site-packages (from httpx->gradio) (1.5.0)\n",
470
- "Requirement already satisfied: sniffio in ./.local/lib/python3.8/site-packages (from httpx->gradio) (1.3.0)\n",
471
  "Requirement already satisfied: certifi in /usr/lib/python3/dist-packages (from httpx->gradio) (2019.11.28)\n",
 
472
  "Requirement already satisfied: httpcore<0.17.0,>=0.15.0 in ./.local/lib/python3.8/site-packages (from httpx->gradio) (0.15.0)\n",
 
473
  "Requirement already satisfied: MarkupSafe>=2.0 in ./.local/lib/python3.8/site-packages (from jinja2->gradio) (2.1.1)\n",
474
  "Requirement already satisfied: mdurl~=0.1 in ./.local/lib/python3.8/site-packages (from markdown-it-py[linkify,plugins]->gradio) (0.1.2)\n",
475
  "Requirement already satisfied: linkify-it-py~=1.0 in ./.local/lib/python3.8/site-packages (from markdown-it-py[linkify,plugins]->gradio) (1.0.3)\n",
476
  "Requirement already satisfied: mdit-py-plugins in ./.local/lib/python3.8/site-packages (from markdown-it-py[linkify,plugins]->gradio) (0.3.3)\n",
477
  "Requirement already satisfied: python-dateutil>=2.7 in ./.local/lib/python3.8/site-packages (from matplotlib->gradio) (2.8.2)\n",
478
- "Requirement already satisfied: kiwisolver>=1.0.1 in /usr/lib/python3/dist-packages (from matplotlib->gradio) (1.0.1)\n",
479
  "Requirement already satisfied: packaging>=20.0 in ./.local/lib/python3.8/site-packages (from matplotlib->gradio) (22.0)\n",
480
- "Requirement already satisfied: cycler>=0.10 in /usr/lib/python3/dist-packages (from matplotlib->gradio) (0.10.0)\n",
481
  "Requirement already satisfied: pyparsing>=2.2.1 in /usr/lib/python3/dist-packages (from matplotlib->gradio) (2.4.6)\n",
 
 
482
  "Requirement already satisfied: fonttools>=4.22.0 in ./.local/lib/python3.8/site-packages (from matplotlib->gradio) (4.38.0)\n",
483
  "Requirement already satisfied: pytz>=2020.1 in ./.local/lib/python3.8/site-packages (from pandas->gradio) (2022.5)\n",
484
- "Requirement already satisfied: bcrypt>=3.1.3 in ./.local/lib/python3.8/site-packages (from paramiko->gradio) (4.0.1)\n",
485
- "Requirement already satisfied: six in /usr/lib/python3/dist-packages (from paramiko->gradio) (1.14.0)\n",
486
  "Requirement already satisfied: pynacl>=1.0.1 in /usr/lib/python3/dist-packages (from paramiko->gradio) (1.3.0)\n",
487
  "Requirement already satisfied: cryptography>=2.5 in /usr/lib/python3/dist-packages (from paramiko->gradio) (2.8)\n",
488
- "Requirement already satisfied: urllib3<1.27,>=1.21.1 in ./.local/lib/python3.8/site-packages (from requests->gradio) (1.26.13)\n",
 
489
  "Requirement already satisfied: idna<4,>=2.5 in /usr/lib/python3/dist-packages (from requests->gradio) (2.8)\n",
 
490
  "Requirement already satisfied: click>=7.0 in /usr/lib/python3/dist-packages (from uvicorn->gradio) (7.0)\n",
491
  "Requirement already satisfied: uc-micro-py in ./.local/lib/python3.8/site-packages (from linkify-it-py~=1.0->markdown-it-py[linkify,plugins]->gradio) (1.0.1)\n",
492
  "Defaulting to user installation because normal site-packages is not writeable\n",
493
- "Requirement already satisfied: more-itertools in /usr/lib/python3/dist-packages (4.2.0)\n"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
494
  ]
495
  }
496
  ],
@@ -500,9 +512,10 @@
500
  "!pip3 install numexpr>=2.7.3\n",
501
  "!pip install librosa\n",
502
  "!pip install evaluate>=0.3.0\n",
503
- "!pip install jiwer\n",
504
  "!pip install gradio\n",
505
- "!pip install more-itertools"
 
 
506
  ]
507
  },
508
  {
@@ -555,7 +568,7 @@
555
  {
556
  "data": {
557
  "application/vnd.jupyter.widget-view+json": {
558
- "model_id": "ad867c59abb44253a78ca06b8853a84d",
559
  "version_major": 2,
560
  "version_minor": 0
561
  },
@@ -739,7 +752,16 @@
739
  "id": "qOwlctMhNmCG",
740
  "tags": []
741
  },
742
- "outputs": [],
 
 
 
 
 
 
 
 
 
743
  "source": [
744
  "ds = load_multiple_streaming_datasets(dataset_names, dataset_config_names=dataset_config_names, text_column_names=text_column_names, use_auth_token=True)\n",
745
  "\n"
@@ -762,7 +784,17 @@
762
  "metadata": {
763
  "id": "imRHJOpm4V_j"
764
  },
765
- "outputs": [],
 
 
 
 
 
 
 
 
 
 
766
  "source": [
767
  "from datasets import IterableDatasetDict\n",
768
  "raw_datasets = IterableDatasetDict()\n",
@@ -817,6 +849,7 @@
817
  "from transformers import WhisperProcessor\n",
818
  "\n",
819
  "processor = WhisperProcessor.from_pretrained(\"emilios/whisper-medium-el\", language=\"Greek\", task=\"transcribe\")\n",
 
820
  "#processor = WhisperProcessor.from_pretrained(\"farsipal/whisper-small-el\", language=\"Greek\", task=\"transcribe\")\n"
821
  ]
822
  },
@@ -995,7 +1028,29 @@
995
  "metadata": {
996
  "id": "a37a7cdb-9013-427f-8de9-6a8d0e9dc684"
997
  },
998
- "outputs": [],
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
999
  "source": [
1000
  "vectorized_datasets = raw_datasets.map(prepare_dataset, remove_columns=list(next(iter(raw_datasets.values())).features)).with_format(\"torch\")"
1001
  ]
@@ -1070,7 +1125,22 @@
1070
  "metadata": {
1071
  "id": "333f7f6e-6053-4d3b-8924-c733c79b82ac"
1072
  },
1073
- "outputs": [],
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1074
  "source": [
1075
  "vectorized_datasets[\"train\"] = vectorized_datasets[\"train\"].filter(\n",
1076
  " is_audio_in_length_range,\n",
@@ -1364,26 +1434,12 @@
1364
  "id": "5a10cc4b-07ec-4ebd-ac1d-7c601023594f",
1365
  "outputId": "b6c255be-8f5e-4045-b9e0-09b8196263d1"
1366
  },
1367
- "outputs": [
1368
- {
1369
- "data": {
1370
- "application/vnd.jupyter.widget-view+json": {
1371
- "model_id": "18e0d00451ec4e10b1cea9b9d3748384",
1372
- "version_major": 2,
1373
- "version_minor": 0
1374
- },
1375
- "text/plain": [
1376
- "Downloading: 0%| | 0.00/3.06G [00:00<?, ?B/s]"
1377
- ]
1378
- },
1379
- "metadata": {},
1380
- "output_type": "display_data"
1381
- }
1382
- ],
1383
  "source": [
1384
  "from transformers import WhisperForConditionalGeneration\n",
1385
  "\n",
1386
- "model = WhisperForConditionalGeneration.from_pretrained(\"emilios/whisper-medium-el\")\n",
 
1387
  "#model = WhisperForConditionalGeneration.from_pretrained(\"farsipal/whisper-small-el\")\n",
1388
  "\n",
1389
  "#model=torch.compile(model0)"
@@ -1458,7 +1514,7 @@
1458
  " #gradient_accumulation_steps=1, # increase by 2x for every 2x decrease in batch size\n",
1459
  " learning_rate=1e-5,\n",
1460
  " warmup_steps=500,\n",
1461
- " max_steps=5000,\n",
1462
  " ignore_data_skip = True,\n",
1463
  " #resume_from_checkpoint=\"checkpoint-4000\",\n",
1464
  " gradient_checkpointing=True,\n",
@@ -1495,7 +1551,7 @@
1495
  "name": "stdout",
1496
  "output_type": "stream",
1497
  "text": [
1498
- "Tue Dec 13 21:29:08 2022 \n",
1499
  "+-----------------------------------------------------------------------------+\n",
1500
  "| NVIDIA-SMI 515.65.01 Driver Version: 515.65.01 CUDA Version: 11.7 |\n",
1501
  "|-------------------------------+----------------------+----------------------+\n",
@@ -1504,7 +1560,7 @@
1504
  "| | | MIG M. |\n",
1505
  "|===============================+======================+======================|\n",
1506
  "| 0 NVIDIA A100-SXM... On | 00000000:06:00.0 Off | 0 |\n",
1507
- "| N/A 32C P0 47W / 400W | 2MiB / 40960MiB | 0% Default |\n",
1508
  "| | | Disabled |\n",
1509
  "+-------------------------------+----------------------+----------------------+\n",
1510
  " \n",
@@ -2275,7 +2331,7 @@
2275
  },
2276
  {
2277
  "cell_type": "code",
2278
- "execution_count": null,
2279
  "id": "ee8b7b8e-1c9a-4d77-9137-1778a629e6de",
2280
  "metadata": {
2281
  "id": "ee8b7b8e-1c9a-4d77-9137-1778a629e6de"
@@ -2285,22 +2341,21 @@
2285
  "name": "stderr",
2286
  "output_type": "stream",
2287
  "text": [
2288
- "Loading model from ./whisper-medium-el/checkpoint-4000.\n",
 
2289
  "/home/ubuntu/.local/lib/python3.8/site-packages/transformers/optimization.py:306: FutureWarning: This implementation of AdamW is deprecated and will be removed in a future version. Use the PyTorch implementation torch.optim.AdamW instead, or set `no_deprecation_warning=True` to disable this warning\n",
2290
  " warnings.warn(\n",
2291
  "***** Running training *****\n",
2292
- " Num examples = 160000\n",
2293
- " Num Epochs = 9223372036854775807\n",
2294
  " Instantaneous batch size per device = 32\n",
2295
  " Total train batch size (w. parallel, distributed & accumulation) = 32\n",
2296
  " Gradient Accumulation steps = 1\n",
2297
- " Total optimization steps = 5000\n",
2298
  " Number of trainable parameters = 763857920\n",
2299
  " Continuing training from checkpoint, will skip to saved global_step\n",
2300
- " Continuing training from epoch 0\n",
2301
- " Continuing training from global step 4000\n",
2302
- "Reading metadata...: 1914it [00:00, 4074.06it/s]\n",
2303
- "The following columns in the training 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"
2304
  ]
2305
  },
2306
  {
@@ -2309,8 +2364,8 @@
2309
  "\n",
2310
  " <div>\n",
2311
  " \n",
2312
- " <progress value='4012' max='5000' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
2313
- " [4012/5000 01:11 < 1:57:29, 0.14 it/s, Epoch 0.00/9223372036854775807]\n",
2314
  " </div>\n",
2315
  " <table border=\"1\" class=\"dataframe\">\n",
2316
  " <thead>\n",
@@ -2318,9 +2373,16 @@
2318
  " <th>Step</th>\n",
2319
  " <th>Training Loss</th>\n",
2320
  " <th>Validation Loss</th>\n",
 
2321
  " </tr>\n",
2322
  " </thead>\n",
2323
  " <tbody>\n",
 
 
 
 
 
 
2324
  " </tbody>\n",
2325
  "</table><p>"
2326
  ],
@@ -2330,6 +2392,51 @@
2330
  },
2331
  "metadata": {},
2332
  "output_type": "display_data"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2333
  }
2334
  ],
2335
  "source": [
@@ -2362,7 +2469,7 @@
2362
  },
2363
  {
2364
  "cell_type": "code",
2365
- "execution_count": null,
2366
  "id": "6dd0e310-9b07-4133-ac14-2ed2d7524e22",
2367
  "metadata": {
2368
  "id": "6dd0e310-9b07-4133-ac14-2ed2d7524e22"
@@ -2394,12 +2501,262 @@
2394
  },
2395
  {
2396
  "cell_type": "code",
2397
- "execution_count": null,
2398
  "id": "95737cda-c5dd-4887-a4d0-dfcb0d61d977",
2399
  "metadata": {
2400
  "id": "95737cda-c5dd-4887-a4d0-dfcb0d61d977"
2401
  },
2402
- "outputs": [],
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2403
  "source": [
2404
  "trainer.push_to_hub(**kwargs)"
2405
  ]
@@ -2419,6 +2776,22 @@
2419
  "metadata": {},
2420
  "outputs": [],
2421
  "source": []
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2422
  }
2423
  ],
2424
  "metadata": {
 
125
  "Requirement already satisfied: torch in ./.local/lib/python3.8/site-packages (1.13.0)\n",
126
  "Requirement already satisfied: torchaudio in ./.local/lib/python3.8/site-packages (0.13.0)\n",
127
  "Requirement already satisfied: torchvision in ./.local/lib/python3.8/site-packages (0.14.0)\n",
 
 
128
  "Requirement already satisfied: nvidia-cublas-cu11==11.10.3.66 in ./.local/lib/python3.8/site-packages (from torch) (11.10.3.66)\n",
 
129
  "Requirement already satisfied: nvidia-cuda-nvrtc-cu11==11.7.99 in ./.local/lib/python3.8/site-packages (from torch) (11.7.99)\n",
130
+ "Requirement already satisfied: nvidia-cudnn-cu11==8.5.0.96 in ./.local/lib/python3.8/site-packages (from torch) (8.5.0.96)\n",
131
+ "Requirement already satisfied: nvidia-cuda-runtime-cu11==11.7.99 in ./.local/lib/python3.8/site-packages (from torch) (11.7.99)\n",
132
+ "Requirement already satisfied: typing-extensions in ./.local/lib/python3.8/site-packages (from torch) (4.4.0)\n",
133
  "Requirement already satisfied: wheel in /usr/lib/python3/dist-packages (from nvidia-cublas-cu11==11.10.3.66->torch) (0.34.2)\n",
134
  "Requirement already satisfied: setuptools in /usr/lib/python3/dist-packages (from nvidia-cublas-cu11==11.10.3.66->torch) (45.2.0)\n",
 
135
  "Requirement already satisfied: requests in ./.local/lib/python3.8/site-packages (from torchvision) (2.28.1)\n",
136
+ "Requirement already satisfied: pillow!=8.3.*,>=5.3.0 in /usr/lib/python3/dist-packages (from torchvision) (7.0.0)\n",
137
  "Requirement already satisfied: numpy in ./.local/lib/python3.8/site-packages (from torchvision) (1.23.5)\n",
138
  "Requirement already satisfied: certifi>=2017.4.17 in /usr/lib/python3/dist-packages (from requests->torchvision) (2019.11.28)\n",
139
  "Requirement already satisfied: charset-normalizer<3,>=2 in ./.local/lib/python3.8/site-packages (from requests->torchvision) (2.1.1)\n",
140
+ "Requirement already satisfied: idna<4,>=2.5 in /usr/lib/python3/dist-packages (from requests->torchvision) (2.8)\n",
141
+ "Requirement already satisfied: urllib3<1.27,>=1.21.1 in ./.local/lib/python3.8/site-packages (from requests->torchvision) (1.26.13)\n"
142
  ]
143
  }
144
  ],
 
200
  "name": "stdout",
201
  "output_type": "stream",
202
  "text": [
203
+ "Wed Dec 14 10:05:55 2022 \n",
204
  "+-----------------------------------------------------------------------------+\n",
205
  "| NVIDIA-SMI 515.65.01 Driver Version: 515.65.01 CUDA Version: 11.7 |\n",
206
  "|-------------------------------+----------------------+----------------------+\n",
 
209
  "| | | MIG M. |\n",
210
  "|===============================+======================+======================|\n",
211
  "| 0 NVIDIA A100-SXM... On | 00000000:06:00.0 Off | 0 |\n",
212
+ "| N/A 31C P0 47W / 400W | 0MiB / 40960MiB | 0% Default |\n",
213
  "| | | Disabled |\n",
214
  "+-------------------------------+----------------------+----------------------+\n",
215
  " \n",
 
261
  "output_type": "stream",
262
  "text": [
263
  "Get:1 https://nvidia.github.io/libnvidia-container/stable/ubuntu18.04/amd64 InRelease [1484 B]\n",
264
+ "Hit:2 https://download.docker.com/linux/ubuntu focal InRelease \n",
265
+ "Hit:3 https://nvidia.github.io/nvidia-container-runtime/stable/ubuntu18.04/amd64 InRelease\n",
266
+ "Hit:4 https://packages.cloud.google.com/apt cloud-sdk InRelease \n",
267
+ "Hit:5 http://archive.lambdalabs.com/ubuntu focal InRelease \n",
268
+ "Get:6 http://security.ubuntu.com/ubuntu focal-security InRelease [114 kB] \n",
269
+ "Hit:7 https://packages.microsoft.com/repos/azure-cli focal InRelease \n",
270
+ "Hit:8 http://archive.ubuntu.com/ubuntu focal InRelease \n",
271
+ "Hit:9 https://pkg.cloudflare.com/cloudflared focal InRelease \n",
272
+ "Ign:10 http://ppa.launchpad.net/jonathonf/ffmpeg-4/ubuntu focal InRelease \n",
273
+ "Get:11 http://archive.ubuntu.com/ubuntu focal-updates InRelease [114 kB] \n",
274
  "Err:12 http://ppa.launchpad.net/jonathonf/ffmpeg-4/ubuntu focal Release \n",
275
  " 404 Not Found [IP: 185.125.190.52 80]\n",
276
  "Hit:13 https://ppa.launchpadcontent.net/deadsnakes/ppa/ubuntu focal InRelease \n",
277
+ "Get:14 http://archive.ubuntu.com/ubuntu focal-backports InRelease [108 kB]\n",
278
+ "Reading package lists... Done \n",
 
 
279
  "E: The repository 'http://ppa.launchpad.net/jonathonf/ffmpeg-4/ubuntu focal Release' does not have a Release file.\n",
280
  "N: Updating from such a repository can't be done securely, and is therefore disabled by default.\n",
281
  "N: See apt-secure(8) manpage for repository creation and user configuration details.\n",
282
+ "Hit:1 https://download.docker.com/linux/ubuntu focal InRelease\n",
283
+ "Get:2 https://nvidia.github.io/libnvidia-container/stable/ubuntu18.04/amd64 InRelease [1484 B]\n",
284
+ "Hit:3 https://nvidia.github.io/nvidia-container-runtime/stable/ubuntu18.04/amd64 InRelease\n",
285
+ "Hit:4 https://packages.cloud.google.com/apt cloud-sdk InRelease \u001b[0m\u001b[33m\n",
286
+ "Hit:5 http://archive.lambdalabs.com/ubuntu focal InRelease \u001b[0m\u001b[33m\n",
287
+ "Hit:6 https://packages.microsoft.com/repos/azure-cli focal InRelease \u001b[0m\u001b[33m\n",
288
+ "Ign:7 http://ppa.launchpad.net/jonathonf/ffmpeg-4/ubuntu focal InRelease \u001b[0m\u001b[33m\n",
289
+ "Hit:8 http://archive.ubuntu.com/ubuntu focal InRelease \u001b[0m\n",
290
+ "Hit:9 http://security.ubuntu.com/ubuntu focal-security InRelease \u001b[0m\u001b[33m\n",
291
+ "Hit:10 https://pkg.cloudflare.com/cloudflared focal InRelease \u001b[0m\n",
292
  "Hit:11 http://archive.ubuntu.com/ubuntu focal-updates InRelease \u001b[0m\n",
293
+ "Hit:12 http://archive.ubuntu.com/ubuntu focal-backports InRelease \u001b[0m\u001b[33m\n",
294
+ "Err:13 http://ppa.launchpad.net/jonathonf/ffmpeg-4/ubuntu focal Release \u001b[33m\n",
295
  " 404 Not Found [IP: 185.125.190.52 80]\n",
296
  "Hit:14 https://ppa.launchpadcontent.net/deadsnakes/ppa/ubuntu focal InRelease\n",
297
  "Reading package lists... Done\u001b[33m\u001b[33m\n",
 
345
  "text": [
346
  "Defaulting to user installation because normal site-packages is not writeable\n",
347
  "Collecting git+https://github.com/huggingface/datasets\n",
348
+ " Cloning https://github.com/huggingface/datasets to /tmp/pip-req-build-klxr8_0g\n",
349
+ " Running command git clone --filter=blob:none --quiet https://github.com/huggingface/datasets /tmp/pip-req-build-klxr8_0g\n",
350
  " Resolved https://github.com/huggingface/datasets to commit c902456677116a081f762fa2b4aad13a0aa04d6e\n",
351
  " Installing build dependencies ... \u001b[?25ldone\n",
352
  "\u001b[?25h Getting requirements to build wheel ... \u001b[?25ldone\n",
353
  "\u001b[?25h Preparing metadata (pyproject.toml) ... \u001b[?25ldone\n",
354
+ "\u001b[?25hRequirement already satisfied: packaging in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (22.0)\n",
355
+ "Requirement already satisfied: pyyaml>=5.1 in /usr/lib/python3/dist-packages (from datasets==2.7.1.dev0) (5.3.1)\n",
356
+ "Requirement already satisfied: multiprocess in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (0.70.14)\n",
357
+ "Requirement already satisfied: dill<0.3.7 in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (0.3.6)\n",
358
+ "Requirement already satisfied: fsspec[http]>=2021.11.1 in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (2022.11.0)\n",
359
  "Requirement already satisfied: aiohttp in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (3.8.3)\n",
 
 
360
  "Requirement already satisfied: pyarrow>=6.0.0 in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (10.0.1)\n",
361
+ "Requirement already satisfied: huggingface-hub<1.0.0,>=0.2.0 in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (0.11.1)\n",
362
  "Requirement already satisfied: responses<0.19 in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (0.18.0)\n",
363
+ "Requirement already satisfied: numpy>=1.17 in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (1.23.5)\n",
364
+ "Requirement already satisfied: xxhash in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (3.1.0)\n",
365
+ "Requirement already satisfied: requests>=2.19.0 in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (2.28.1)\n",
366
  "Requirement already satisfied: pandas in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (1.5.1)\n",
367
  "Requirement already satisfied: tqdm>=4.62.1 in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (4.64.1)\n",
 
 
368
  "Requirement already satisfied: yarl<2.0,>=1.0 in ./.local/lib/python3.8/site-packages (from aiohttp->datasets==2.7.1.dev0) (1.8.2)\n",
369
+ "Requirement already satisfied: charset-normalizer<3.0,>=2.0 in ./.local/lib/python3.8/site-packages (from aiohttp->datasets==2.7.1.dev0) (2.1.1)\n",
370
+ "Requirement already satisfied: async-timeout<5.0,>=4.0.0a3 in ./.local/lib/python3.8/site-packages (from aiohttp->datasets==2.7.1.dev0) (4.0.2)\n",
371
  "Requirement already satisfied: aiosignal>=1.1.2 in ./.local/lib/python3.8/site-packages (from aiohttp->datasets==2.7.1.dev0) (1.3.1)\n",
372
+ "Requirement already satisfied: frozenlist>=1.1.1 in ./.local/lib/python3.8/site-packages (from aiohttp->datasets==2.7.1.dev0) (1.3.3)\n",
373
  "Requirement already satisfied: multidict<7.0,>=4.5 in ./.local/lib/python3.8/site-packages (from aiohttp->datasets==2.7.1.dev0) (6.0.3)\n",
374
  "Requirement already satisfied: attrs>=17.3.0 in /usr/lib/python3/dist-packages (from aiohttp->datasets==2.7.1.dev0) (19.3.0)\n",
 
 
 
375
  "Requirement already satisfied: filelock in /usr/lib/python3/dist-packages (from huggingface-hub<1.0.0,>=0.2.0->datasets==2.7.1.dev0) (3.0.12)\n",
376
  "Requirement already satisfied: typing-extensions>=3.7.4.3 in ./.local/lib/python3.8/site-packages (from huggingface-hub<1.0.0,>=0.2.0->datasets==2.7.1.dev0) (4.4.0)\n",
 
377
  "Requirement already satisfied: urllib3<1.27,>=1.21.1 in ./.local/lib/python3.8/site-packages (from requests>=2.19.0->datasets==2.7.1.dev0) (1.26.13)\n",
378
  "Requirement already satisfied: idna<4,>=2.5 in /usr/lib/python3/dist-packages (from requests>=2.19.0->datasets==2.7.1.dev0) (2.8)\n",
379
+ "Requirement already satisfied: certifi>=2017.4.17 in /usr/lib/python3/dist-packages (from requests>=2.19.0->datasets==2.7.1.dev0) (2019.11.28)\n",
380
  "Requirement already satisfied: pytz>=2020.1 in ./.local/lib/python3.8/site-packages (from pandas->datasets==2.7.1.dev0) (2022.5)\n",
381
+ "Requirement already satisfied: python-dateutil>=2.8.1 in ./.local/lib/python3.8/site-packages (from pandas->datasets==2.7.1.dev0) (2.8.2)\n",
382
  "Requirement already satisfied: six>=1.5 in /usr/lib/python3/dist-packages (from python-dateutil>=2.8.1->pandas->datasets==2.7.1.dev0) (1.14.0)\n",
383
  "Defaulting to user installation because normal site-packages is not writeable\n",
384
  "Collecting git+https://github.com/huggingface/transformers\n",
385
+ " Cloning https://github.com/huggingface/transformers to /tmp/pip-req-build-fqy16y_p\n",
386
+ " Running command git clone --filter=blob:none --quiet https://github.com/huggingface/transformers /tmp/pip-req-build-fqy16y_p\n",
387
  " Resolved https://github.com/huggingface/transformers to commit d994473b05a83ea398d9f10ca458855df095e22d\n",
388
  " Installing build dependencies ... \u001b[?25ldone\n",
389
  "\u001b[?25h Getting requirements to build wheel ... \u001b[?25ldone\n",
390
  "\u001b[?25h Preparing metadata (pyproject.toml) ... \u001b[?25ldone\n",
391
+ "\u001b[?25hRequirement already satisfied: tqdm>=4.27 in ./.local/lib/python3.8/site-packages (from transformers==4.26.0.dev0) (4.64.1)\n",
 
 
 
 
392
  "Requirement already satisfied: pyyaml>=5.1 in /usr/lib/python3/dist-packages (from transformers==4.26.0.dev0) (5.3.1)\n",
393
  "Requirement already satisfied: requests in ./.local/lib/python3.8/site-packages (from transformers==4.26.0.dev0) (2.28.1)\n",
394
+ "Requirement already satisfied: numpy>=1.17 in ./.local/lib/python3.8/site-packages (from transformers==4.26.0.dev0) (1.23.5)\n",
395
+ "Requirement already satisfied: packaging>=20.0 in ./.local/lib/python3.8/site-packages (from transformers==4.26.0.dev0) (22.0)\n",
396
+ "Requirement already satisfied: tokenizers!=0.11.3,<0.14,>=0.11.1 in ./.local/lib/python3.8/site-packages (from transformers==4.26.0.dev0) (0.13.2)\n",
397
+ "Requirement already satisfied: filelock in /usr/lib/python3/dist-packages (from transformers==4.26.0.dev0) (3.0.12)\n",
398
+ "Requirement already satisfied: huggingface-hub<1.0,>=0.10.0 in ./.local/lib/python3.8/site-packages (from transformers==4.26.0.dev0) (0.11.1)\n",
399
  "Requirement already satisfied: regex!=2019.12.17 in ./.local/lib/python3.8/site-packages (from transformers==4.26.0.dev0) (2022.10.31)\n",
 
400
  "Requirement already satisfied: typing-extensions>=3.7.4.3 in ./.local/lib/python3.8/site-packages (from huggingface-hub<1.0,>=0.10.0->transformers==4.26.0.dev0) (4.4.0)\n",
 
401
  "Requirement already satisfied: idna<4,>=2.5 in /usr/lib/python3/dist-packages (from requests->transformers==4.26.0.dev0) (2.8)\n",
 
402
  "Requirement already satisfied: urllib3<1.27,>=1.21.1 in ./.local/lib/python3.8/site-packages (from requests->transformers==4.26.0.dev0) (1.26.13)\n",
403
+ "Requirement already satisfied: certifi>=2017.4.17 in /usr/lib/python3/dist-packages (from requests->transformers==4.26.0.dev0) (2019.11.28)\n",
404
+ "Requirement already satisfied: charset-normalizer<3,>=2 in ./.local/lib/python3.8/site-packages (from requests->transformers==4.26.0.dev0) (2.1.1)\n",
405
  "Defaulting to user installation because normal site-packages is not writeable\n",
406
  "Requirement already satisfied: librosa in ./.local/lib/python3.8/site-packages (0.9.2)\n",
407
+ "Requirement already satisfied: scipy>=1.2.0 in ./.local/lib/python3.8/site-packages (from librosa) (1.9.3)\n",
 
 
408
  "Requirement already satisfied: numpy>=1.17.0 in ./.local/lib/python3.8/site-packages (from librosa) (1.23.5)\n",
 
 
409
  "Requirement already satisfied: audioread>=2.1.9 in ./.local/lib/python3.8/site-packages (from librosa) (3.0.0)\n",
410
+ "Requirement already satisfied: decorator>=4.0.10 in /usr/lib/python3/dist-packages (from librosa) (4.4.2)\n",
411
+ "Requirement already satisfied: joblib>=0.14 in ./.local/lib/python3.8/site-packages (from librosa) (1.2.0)\n",
412
  "Requirement already satisfied: packaging>=20.0 in ./.local/lib/python3.8/site-packages (from librosa) (22.0)\n",
413
  "Requirement already satisfied: resampy>=0.2.2 in ./.local/lib/python3.8/site-packages (from librosa) (0.4.2)\n",
414
+ "Requirement already satisfied: numba>=0.45.1 in ./.local/lib/python3.8/site-packages (from librosa) (0.56.4)\n",
415
+ "Requirement already satisfied: soundfile>=0.10.2 in ./.local/lib/python3.8/site-packages (from librosa) (0.11.0)\n",
416
+ "Requirement already satisfied: pooch>=1.0 in ./.local/lib/python3.8/site-packages (from librosa) (1.6.0)\n",
417
+ "Requirement already satisfied: scikit-learn>=0.19.1 in /usr/lib/python3/dist-packages (from librosa) (0.22.2.post1)\n",
418
  "Requirement already satisfied: llvmlite<0.40,>=0.39.0dev0 in ./.local/lib/python3.8/site-packages (from numba>=0.45.1->librosa) (0.39.1)\n",
419
  "Requirement already satisfied: importlib-metadata in ./.local/lib/python3.8/site-packages (from numba>=0.45.1->librosa) (5.0.0)\n",
420
+ "Requirement already satisfied: setuptools in /usr/lib/python3/dist-packages (from numba>=0.45.1->librosa) (45.2.0)\n",
421
  "Requirement already satisfied: appdirs>=1.3.0 in /usr/lib/python3/dist-packages (from pooch>=1.0->librosa) (1.4.3)\n",
422
+ "Requirement already satisfied: requests>=2.19.0 in ./.local/lib/python3.8/site-packages (from pooch>=1.0->librosa) (2.28.1)\n",
423
  "Requirement already satisfied: cffi>=1.0 in /usr/lib/python3/dist-packages (from soundfile>=0.10.2->librosa) (1.14.0)\n",
 
 
424
  "Requirement already satisfied: charset-normalizer<3,>=2 in ./.local/lib/python3.8/site-packages (from requests>=2.19.0->pooch>=1.0->librosa) (2.1.1)\n",
425
+ "Requirement already satisfied: idna<4,>=2.5 in /usr/lib/python3/dist-packages (from requests>=2.19.0->pooch>=1.0->librosa) (2.8)\n",
426
+ "Requirement already satisfied: certifi>=2017.4.17 in /usr/lib/python3/dist-packages (from requests>=2.19.0->pooch>=1.0->librosa) (2019.11.28)\n",
427
  "Requirement already satisfied: urllib3<1.27,>=1.21.1 in ./.local/lib/python3.8/site-packages (from requests>=2.19.0->pooch>=1.0->librosa) (1.26.13)\n",
428
  "Requirement already satisfied: zipp>=0.5 in /usr/lib/python3/dist-packages (from importlib-metadata->numba>=0.45.1->librosa) (1.0.0)\n",
429
  "Defaulting to user installation because normal site-packages is not writeable\n",
 
 
 
 
430
  "Requirement already satisfied: gradio in ./.local/lib/python3.8/site-packages (3.13.0)\n",
 
 
 
 
 
 
431
  "Requirement already satisfied: pillow in /usr/lib/python3/dist-packages (from gradio) (7.0.0)\n",
432
+ "Requirement already satisfied: pydub in ./.local/lib/python3.8/site-packages (from gradio) (0.25.1)\n",
 
 
 
 
 
 
 
433
  "Requirement already satisfied: pydantic in ./.local/lib/python3.8/site-packages (from gradio) (1.10.2)\n",
 
434
  "Requirement already satisfied: ffmpy in ./.local/lib/python3.8/site-packages (from gradio) (0.3.0)\n",
435
+ "Requirement already satisfied: markdown-it-py[linkify,plugins] in ./.local/lib/python3.8/site-packages (from gradio) (2.1.0)\n",
436
  "Requirement already satisfied: fastapi in ./.local/lib/python3.8/site-packages (from gradio) (0.88.0)\n",
437
+ "Requirement already satisfied: orjson in ./.local/lib/python3.8/site-packages (from gradio) (3.8.3)\n",
438
+ "Requirement already satisfied: pandas in ./.local/lib/python3.8/site-packages (from gradio) (1.5.1)\n",
439
+ "Requirement already satisfied: pyyaml in /usr/lib/python3/dist-packages (from gradio) (5.3.1)\n",
440
+ "Requirement already satisfied: websockets>=10.0 in ./.local/lib/python3.8/site-packages (from gradio) (10.4)\n",
441
+ "Requirement already satisfied: requests in ./.local/lib/python3.8/site-packages (from gradio) (2.28.1)\n",
442
+ "Requirement already satisfied: h11<0.13,>=0.11 in ./.local/lib/python3.8/site-packages (from gradio) (0.12.0)\n",
443
+ "Requirement already satisfied: numpy in ./.local/lib/python3.8/site-packages (from gradio) (1.23.5)\n",
444
+ "Requirement already satisfied: python-multipart in ./.local/lib/python3.8/site-packages (from gradio) (0.0.5)\n",
445
+ "Requirement already satisfied: pycryptodome in ./.local/lib/python3.8/site-packages (from gradio) (3.16.0)\n",
446
  "Requirement already satisfied: jinja2 in ./.local/lib/python3.8/site-packages (from gradio) (3.1.2)\n",
447
+ "Requirement already satisfied: fsspec in ./.local/lib/python3.8/site-packages (from gradio) (2022.11.0)\n",
448
  "Requirement already satisfied: matplotlib in ./.local/lib/python3.8/site-packages (from gradio) (3.5.3)\n",
449
+ "Requirement already satisfied: uvicorn in ./.local/lib/python3.8/site-packages (from gradio) (0.20.0)\n",
450
+ "Requirement already satisfied: paramiko in ./.local/lib/python3.8/site-packages (from gradio) (2.12.0)\n",
451
+ "Requirement already satisfied: httpx in ./.local/lib/python3.8/site-packages (from gradio) (0.23.1)\n",
452
+ "Requirement already satisfied: aiohttp in ./.local/lib/python3.8/site-packages (from gradio) (3.8.3)\n",
453
+ "Requirement already satisfied: charset-normalizer<3.0,>=2.0 in ./.local/lib/python3.8/site-packages (from aiohttp->gradio) (2.1.1)\n",
454
  "Requirement already satisfied: multidict<7.0,>=4.5 in ./.local/lib/python3.8/site-packages (from aiohttp->gradio) (6.0.3)\n",
 
455
  "Requirement already satisfied: attrs>=17.3.0 in /usr/lib/python3/dist-packages (from aiohttp->gradio) (19.3.0)\n",
 
 
456
  "Requirement already satisfied: yarl<2.0,>=1.0 in ./.local/lib/python3.8/site-packages (from aiohttp->gradio) (1.8.2)\n",
457
+ "Requirement already satisfied: aiosignal>=1.1.2 in ./.local/lib/python3.8/site-packages (from aiohttp->gradio) (1.3.1)\n",
458
+ "Requirement already satisfied: frozenlist>=1.1.1 in ./.local/lib/python3.8/site-packages (from aiohttp->gradio) (1.3.3)\n",
459
+ "Requirement already satisfied: async-timeout<5.0,>=4.0.0a3 in ./.local/lib/python3.8/site-packages (from aiohttp->gradio) (4.0.2)\n",
460
  "Requirement already satisfied: starlette==0.22.0 in ./.local/lib/python3.8/site-packages (from fastapi->gradio) (0.22.0)\n",
 
461
  "Requirement already satisfied: anyio<5,>=3.4.0 in ./.local/lib/python3.8/site-packages (from starlette==0.22.0->fastapi->gradio) (3.6.2)\n",
462
+ "Requirement already satisfied: typing-extensions>=3.10.0 in ./.local/lib/python3.8/site-packages (from starlette==0.22.0->fastapi->gradio) (4.4.0)\n",
 
463
  "Requirement already satisfied: certifi in /usr/lib/python3/dist-packages (from httpx->gradio) (2019.11.28)\n",
464
+ "Requirement already satisfied: sniffio in ./.local/lib/python3.8/site-packages (from httpx->gradio) (1.3.0)\n",
465
  "Requirement already satisfied: httpcore<0.17.0,>=0.15.0 in ./.local/lib/python3.8/site-packages (from httpx->gradio) (0.15.0)\n",
466
+ "Requirement already satisfied: rfc3986[idna2008]<2,>=1.3 in ./.local/lib/python3.8/site-packages (from httpx->gradio) (1.5.0)\n",
467
  "Requirement already satisfied: MarkupSafe>=2.0 in ./.local/lib/python3.8/site-packages (from jinja2->gradio) (2.1.1)\n",
468
  "Requirement already satisfied: mdurl~=0.1 in ./.local/lib/python3.8/site-packages (from markdown-it-py[linkify,plugins]->gradio) (0.1.2)\n",
469
  "Requirement already satisfied: linkify-it-py~=1.0 in ./.local/lib/python3.8/site-packages (from markdown-it-py[linkify,plugins]->gradio) (1.0.3)\n",
470
  "Requirement already satisfied: mdit-py-plugins in ./.local/lib/python3.8/site-packages (from markdown-it-py[linkify,plugins]->gradio) (0.3.3)\n",
471
  "Requirement already satisfied: python-dateutil>=2.7 in ./.local/lib/python3.8/site-packages (from matplotlib->gradio) (2.8.2)\n",
 
472
  "Requirement already satisfied: packaging>=20.0 in ./.local/lib/python3.8/site-packages (from matplotlib->gradio) (22.0)\n",
 
473
  "Requirement already satisfied: pyparsing>=2.2.1 in /usr/lib/python3/dist-packages (from matplotlib->gradio) (2.4.6)\n",
474
+ "Requirement already satisfied: kiwisolver>=1.0.1 in /usr/lib/python3/dist-packages (from matplotlib->gradio) (1.0.1)\n",
475
+ "Requirement already satisfied: cycler>=0.10 in /usr/lib/python3/dist-packages (from matplotlib->gradio) (0.10.0)\n",
476
  "Requirement already satisfied: fonttools>=4.22.0 in ./.local/lib/python3.8/site-packages (from matplotlib->gradio) (4.38.0)\n",
477
  "Requirement already satisfied: pytz>=2020.1 in ./.local/lib/python3.8/site-packages (from pandas->gradio) (2022.5)\n",
 
 
478
  "Requirement already satisfied: pynacl>=1.0.1 in /usr/lib/python3/dist-packages (from paramiko->gradio) (1.3.0)\n",
479
  "Requirement already satisfied: cryptography>=2.5 in /usr/lib/python3/dist-packages (from paramiko->gradio) (2.8)\n",
480
+ "Requirement already satisfied: six in /usr/lib/python3/dist-packages (from paramiko->gradio) (1.14.0)\n",
481
+ "Requirement already satisfied: bcrypt>=3.1.3 in ./.local/lib/python3.8/site-packages (from paramiko->gradio) (4.0.1)\n",
482
  "Requirement already satisfied: idna<4,>=2.5 in /usr/lib/python3/dist-packages (from requests->gradio) (2.8)\n",
483
+ "Requirement already satisfied: urllib3<1.27,>=1.21.1 in ./.local/lib/python3.8/site-packages (from requests->gradio) (1.26.13)\n",
484
  "Requirement already satisfied: click>=7.0 in /usr/lib/python3/dist-packages (from uvicorn->gradio) (7.0)\n",
485
  "Requirement already satisfied: uc-micro-py in ./.local/lib/python3.8/site-packages (from linkify-it-py~=1.0->markdown-it-py[linkify,plugins]->gradio) (1.0.1)\n",
486
  "Defaulting to user installation because normal site-packages is not writeable\n",
487
+ "Requirement already satisfied: more-itertools in /usr/lib/python3/dist-packages (4.2.0)\n",
488
+ "Defaulting to user installation because normal site-packages is not writeable\n",
489
+ "Requirement already satisfied: jiwer in ./.local/lib/python3.8/site-packages (2.5.1)\n",
490
+ "Requirement already satisfied: bitsandbytes in ./.local/lib/python3.8/site-packages (0.35.4)\n",
491
+ "Requirement already satisfied: accelerate in ./.local/lib/python3.8/site-packages (0.15.0)\n",
492
+ "Requirement already satisfied: levenshtein==0.20.2 in ./.local/lib/python3.8/site-packages (from jiwer) (0.20.2)\n",
493
+ "Requirement already satisfied: rapidfuzz<3.0.0,>=2.3.0 in ./.local/lib/python3.8/site-packages (from levenshtein==0.20.2->jiwer) (2.13.6)\n",
494
+ "Requirement already satisfied: torch>=1.4.0 in ./.local/lib/python3.8/site-packages (from accelerate) (1.13.0)\n",
495
+ "Requirement already satisfied: packaging>=20.0 in ./.local/lib/python3.8/site-packages (from accelerate) (22.0)\n",
496
+ "Requirement already satisfied: numpy>=1.17 in ./.local/lib/python3.8/site-packages (from accelerate) (1.23.5)\n",
497
+ "Requirement already satisfied: pyyaml in /usr/lib/python3/dist-packages (from accelerate) (5.3.1)\n",
498
+ "Requirement already satisfied: psutil in /usr/lib/python3/dist-packages (from accelerate) (5.5.1)\n",
499
+ "Requirement already satisfied: nvidia-cuda-runtime-cu11==11.7.99 in ./.local/lib/python3.8/site-packages (from torch>=1.4.0->accelerate) (11.7.99)\n",
500
+ "Requirement already satisfied: typing-extensions in ./.local/lib/python3.8/site-packages (from torch>=1.4.0->accelerate) (4.4.0)\n",
501
+ "Requirement already satisfied: nvidia-cublas-cu11==11.10.3.66 in ./.local/lib/python3.8/site-packages (from torch>=1.4.0->accelerate) (11.10.3.66)\n",
502
+ "Requirement already satisfied: nvidia-cuda-nvrtc-cu11==11.7.99 in ./.local/lib/python3.8/site-packages (from torch>=1.4.0->accelerate) (11.7.99)\n",
503
+ "Requirement already satisfied: nvidia-cudnn-cu11==8.5.0.96 in ./.local/lib/python3.8/site-packages (from torch>=1.4.0->accelerate) (8.5.0.96)\n",
504
+ "Requirement already satisfied: setuptools in /usr/lib/python3/dist-packages (from nvidia-cublas-cu11==11.10.3.66->torch>=1.4.0->accelerate) (45.2.0)\n",
505
+ "Requirement already satisfied: wheel in /usr/lib/python3/dist-packages (from nvidia-cublas-cu11==11.10.3.66->torch>=1.4.0->accelerate) (0.34.2)\n"
506
  ]
507
  }
508
  ],
 
512
  "!pip3 install numexpr>=2.7.3\n",
513
  "!pip install librosa\n",
514
  "!pip install evaluate>=0.3.0\n",
 
515
  "!pip install gradio\n",
516
+ "!pip install more-itertools\n",
517
+ "!pip install jiwer \n",
518
+ "#!pip install bitsandbytes accelerate"
519
  ]
520
  },
521
  {
 
568
  {
569
  "data": {
570
  "application/vnd.jupyter.widget-view+json": {
571
+ "model_id": "54def7c3052c464b960445d9650f571a",
572
  "version_major": 2,
573
  "version_minor": 0
574
  },
 
752
  "id": "qOwlctMhNmCG",
753
  "tags": []
754
  },
755
+ "outputs": [
756
+ {
757
+ "name": "stderr",
758
+ "output_type": "stream",
759
+ "text": [
760
+ "Found cached dataset common_voice_11_0 (/home/ubuntu/.cache/huggingface/datasets/mozilla-foundation___common_voice_11_0/el/11.0.0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f)\n",
761
+ "Found cached dataset fleurs (/home/ubuntu/.cache/huggingface/datasets/google___fleurs/el_gr/2.0.0/aabb39fb29739c495517ac904e2886819b6e344702f0a5b5283cb178b087c94a)\n"
762
+ ]
763
+ }
764
+ ],
765
  "source": [
766
  "ds = load_multiple_streaming_datasets(dataset_names, dataset_config_names=dataset_config_names, text_column_names=text_column_names, use_auth_token=True)\n",
767
  "\n"
 
784
  "metadata": {
785
  "id": "imRHJOpm4V_j"
786
  },
787
+ "outputs": [
788
+ {
789
+ "name": "stderr",
790
+ "output_type": "stream",
791
+ "text": [
792
+ "Found cached dataset common_voice_11_0 (/home/ubuntu/.cache/huggingface/datasets/mozilla-foundation___common_voice_11_0/el/11.0.0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f)\n",
793
+ "Found cached dataset fleurs (/home/ubuntu/.cache/huggingface/datasets/google___fleurs/el_gr/2.0.0/aabb39fb29739c495517ac904e2886819b6e344702f0a5b5283cb178b087c94a)\n",
794
+ "Found cached dataset common_voice_11_0 (/home/ubuntu/.cache/huggingface/datasets/mozilla-foundation___common_voice_11_0/el/11.0.0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f)\n"
795
+ ]
796
+ }
797
+ ],
798
  "source": [
799
  "from datasets import IterableDatasetDict\n",
800
  "raw_datasets = IterableDatasetDict()\n",
 
849
  "from transformers import WhisperProcessor\n",
850
  "\n",
851
  "processor = WhisperProcessor.from_pretrained(\"emilios/whisper-medium-el\", language=\"Greek\", task=\"transcribe\")\n",
852
+ "#processor = WhisperProcessor.from_pretrained(\"emilios/whisper-medium-el\", language=\"Greek\", task=\"transcribe\", load_in_8bit=True)\n",
853
  "#processor = WhisperProcessor.from_pretrained(\"farsipal/whisper-small-el\", language=\"Greek\", task=\"transcribe\")\n"
854
  ]
855
  },
 
1028
  "metadata": {
1029
  "id": "a37a7cdb-9013-427f-8de9-6a8d0e9dc684"
1030
  },
1031
+ "outputs": [
1032
+ {
1033
+ "data": {
1034
+ "application/vnd.jupyter.widget-view+json": {
1035
+ "model_id": "1d964121a24b4f4dbd3ce7b21112b05c",
1036
+ "version_major": 2,
1037
+ "version_minor": 0
1038
+ },
1039
+ "text/plain": [
1040
+ " 0%| | 0/6430 [00:00<?, ?ex/s]"
1041
+ ]
1042
+ },
1043
+ "metadata": {},
1044
+ "output_type": "display_data"
1045
+ },
1046
+ {
1047
+ "name": "stderr",
1048
+ "output_type": "stream",
1049
+ "text": [
1050
+ "Loading cached processed dataset at /home/ubuntu/.cache/huggingface/datasets/mozilla-foundation___common_voice_11_0/el/11.0.0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f/cache-52a8b70c074fdab6.arrow\n"
1051
+ ]
1052
+ }
1053
+ ],
1054
  "source": [
1055
  "vectorized_datasets = raw_datasets.map(prepare_dataset, remove_columns=list(next(iter(raw_datasets.values())).features)).with_format(\"torch\")"
1056
  ]
 
1125
  "metadata": {
1126
  "id": "333f7f6e-6053-4d3b-8924-c733c79b82ac"
1127
  },
1128
+ "outputs": [
1129
+ {
1130
+ "data": {
1131
+ "application/vnd.jupyter.widget-view+json": {
1132
+ "model_id": "197e7f4ef7bb4568b18cdacf32ae8791",
1133
+ "version_major": 2,
1134
+ "version_minor": 0
1135
+ },
1136
+ "text/plain": [
1137
+ " 0%| | 0/7 [00:00<?, ?ba/s]"
1138
+ ]
1139
+ },
1140
+ "metadata": {},
1141
+ "output_type": "display_data"
1142
+ }
1143
+ ],
1144
  "source": [
1145
  "vectorized_datasets[\"train\"] = vectorized_datasets[\"train\"].filter(\n",
1146
  " is_audio_in_length_range,\n",
 
1434
  "id": "5a10cc4b-07ec-4ebd-ac1d-7c601023594f",
1435
  "outputId": "b6c255be-8f5e-4045-b9e0-09b8196263d1"
1436
  },
1437
+ "outputs": [],
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1438
  "source": [
1439
  "from transformers import WhisperForConditionalGeneration\n",
1440
  "\n",
1441
+ "model = WhisperForConditionalGeneration.from_pretrained(\"emilios/whisper-medium-el\" )\n",
1442
+ "#model = WhisperForConditionalGeneration.from_pretrained(\"emilios/whisper-medium-el\", device_map='auto', load_in_8bit=True)\n",
1443
  "#model = WhisperForConditionalGeneration.from_pretrained(\"farsipal/whisper-small-el\")\n",
1444
  "\n",
1445
  "#model=torch.compile(model0)"
 
1514
  " #gradient_accumulation_steps=1, # increase by 2x for every 2x decrease in batch size\n",
1515
  " learning_rate=1e-5,\n",
1516
  " warmup_steps=500,\n",
1517
+ " max_steps=7000,\n",
1518
  " ignore_data_skip = True,\n",
1519
  " #resume_from_checkpoint=\"checkpoint-4000\",\n",
1520
  " gradient_checkpointing=True,\n",
 
1551
  "name": "stdout",
1552
  "output_type": "stream",
1553
  "text": [
1554
+ "Wed Dec 14 10:24:09 2022 \n",
1555
  "+-----------------------------------------------------------------------------+\n",
1556
  "| NVIDIA-SMI 515.65.01 Driver Version: 515.65.01 CUDA Version: 11.7 |\n",
1557
  "|-------------------------------+----------------------+----------------------+\n",
 
1560
  "| | | MIG M. |\n",
1561
  "|===============================+======================+======================|\n",
1562
  "| 0 NVIDIA A100-SXM... On | 00000000:06:00.0 Off | 0 |\n",
1563
+ "| N/A 31C P0 46W / 400W | 2MiB / 40960MiB | 0% Default |\n",
1564
  "| | | Disabled |\n",
1565
  "+-------------------------------+----------------------+----------------------+\n",
1566
  " \n",
 
2331
  },
2332
  {
2333
  "cell_type": "code",
2334
+ "execution_count": 31,
2335
  "id": "ee8b7b8e-1c9a-4d77-9137-1778a629e6de",
2336
  "metadata": {
2337
  "id": "ee8b7b8e-1c9a-4d77-9137-1778a629e6de"
 
2341
  "name": "stderr",
2342
  "output_type": "stream",
2343
  "text": [
2344
+ "Loading model from ./whisper-medium-el/checkpoint-6000.\n",
2345
+ "The following columns in the training 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",
2346
  "/home/ubuntu/.local/lib/python3.8/site-packages/transformers/optimization.py:306: FutureWarning: This implementation of AdamW is deprecated and will be removed in a future version. Use the PyTorch implementation torch.optim.AdamW instead, or set `no_deprecation_warning=True` to disable this warning\n",
2347
  " warnings.warn(\n",
2348
  "***** Running training *****\n",
2349
+ " Num examples = 6428\n",
2350
+ " Num Epochs = 35\n",
2351
  " Instantaneous batch size per device = 32\n",
2352
  " Total train batch size (w. parallel, distributed & accumulation) = 32\n",
2353
  " Gradient Accumulation steps = 1\n",
2354
+ " Total optimization steps = 7000\n",
2355
  " Number of trainable parameters = 763857920\n",
2356
  " Continuing training from checkpoint, will skip to saved global_step\n",
2357
+ " Continuing training from epoch 29\n",
2358
+ " Continuing training from global step 6000\n"
 
 
2359
  ]
2360
  },
2361
  {
 
2364
  "\n",
2365
  " <div>\n",
2366
  " \n",
2367
+ " <progress value='7001' max='7000' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
2368
+ " [7000/7000 1:21:59, Epoch 33.98/35]\n",
2369
  " </div>\n",
2370
  " <table border=\"1\" class=\"dataframe\">\n",
2371
  " <thead>\n",
 
2373
  " <th>Step</th>\n",
2374
  " <th>Training Loss</th>\n",
2375
  " <th>Validation Loss</th>\n",
2376
+ " <th>Wer</th>\n",
2377
  " </tr>\n",
2378
  " </thead>\n",
2379
  " <tbody>\n",
2380
+ " <tr>\n",
2381
+ " <td>7000</td>\n",
2382
+ " <td>0.000400</td>\n",
2383
+ " <td>0.385369</td>\n",
2384
+ " <td>11.450594</td>\n",
2385
+ " </tr>\n",
2386
  " </tbody>\n",
2387
  "</table><p>"
2388
  ],
 
2392
  },
2393
  "metadata": {},
2394
  "output_type": "display_data"
2395
+ },
2396
+ {
2397
+ "name": "stderr",
2398
+ "output_type": "stream",
2399
+ "text": [
2400
+ "The following columns in the evaluation set don't have a corresponding argument in `WhisperForConditionalGeneration.forward` and have been ignored: down_votes, locale, age, client_id, accent, input_length, gender, path, segment, up_votes. If down_votes, locale, age, client_id, accent, input_length, gender, path, segment, up_votes are not expected by `WhisperForConditionalGeneration.forward`, you can safely ignore this message.\n",
2401
+ "***** Running Evaluation *****\n",
2402
+ " Num examples = 1696\n",
2403
+ " Batch size = 16\n",
2404
+ "Saving model checkpoint to ./whisper-medium-el/checkpoint-7000\n",
2405
+ "Configuration saved in ./whisper-medium-el/checkpoint-7000/config.json\n",
2406
+ "Model weights saved in ./whisper-medium-el/checkpoint-7000/pytorch_model.bin\n",
2407
+ "Feature extractor saved in ./whisper-medium-el/checkpoint-7000/preprocessor_config.json\n",
2408
+ "tokenizer config file saved in ./whisper-medium-el/checkpoint-7000/tokenizer_config.json\n",
2409
+ "Special tokens file saved in ./whisper-medium-el/checkpoint-7000/special_tokens_map.json\n",
2410
+ "added tokens file saved in ./whisper-medium-el/checkpoint-7000/added_tokens.json\n",
2411
+ "Feature extractor saved in ./whisper-medium-el/preprocessor_config.json\n",
2412
+ "tokenizer config file saved in ./whisper-medium-el/tokenizer_config.json\n",
2413
+ "Special tokens file saved in ./whisper-medium-el/special_tokens_map.json\n",
2414
+ "added tokens file saved in ./whisper-medium-el/added_tokens.json\n"
2415
+ ]
2416
+ },
2417
+ {
2418
+ "ename": "OSError",
2419
+ "evalue": "error: insufficient permission for adding an object to repository database .git/objects\nerror: e5_interleaving-resume.ipynb: failed to insert into database\nerror: unable to index file 'e5_interleaving-resume.ipynb'\nfatal: adding files failed\n",
2420
+ "output_type": "error",
2421
+ "traceback": [
2422
+ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
2423
+ "\u001b[0;31mCalledProcessError\u001b[0m Traceback (most recent call last)",
2424
+ "\u001b[0;32m~/.local/lib/python3.8/site-packages/huggingface_hub/repository.py\u001b[0m in \u001b[0;36mgit_add\u001b[0;34m(self, pattern, auto_lfs_track)\u001b[0m\n\u001b[1;32m 1121\u001b[0m \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1122\u001b[0;31m \u001b[0mresult\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mrun_subprocess\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"git add -v\"\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msplit\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0mpattern\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mlocal_dir\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1123\u001b[0m \u001b[0mlogger\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0minfo\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34mf\"Adding to index:\\n{result.stdout}\\n\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
2425
+ "\u001b[0;32m~/.local/lib/python3.8/site-packages/huggingface_hub/utils/_subprocess.py\u001b[0m in \u001b[0;36mrun_subprocess\u001b[0;34m(command, folder, check, **kwargs)\u001b[0m\n\u001b[1;32m 60\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 61\u001b[0;31m return subprocess.run(\n\u001b[0m\u001b[1;32m 62\u001b[0m \u001b[0mcommand\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
2426
+ "\u001b[0;32m/usr/lib/python3.8/subprocess.py\u001b[0m in \u001b[0;36mrun\u001b[0;34m(input, capture_output, timeout, check, *popenargs, **kwargs)\u001b[0m\n\u001b[1;32m 515\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mcheck\u001b[0m \u001b[0;32mand\u001b[0m \u001b[0mretcode\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 516\u001b[0;31m raise CalledProcessError(retcode, process.args,\n\u001b[0m\u001b[1;32m 517\u001b[0m output=stdout, stderr=stderr)\n",
2427
+ "\u001b[0;31mCalledProcessError\u001b[0m: Command '['git', 'add', '-v', '.']' returned non-zero exit status 128.",
2428
+ "\nDuring handling of the above exception, another exception occurred:\n",
2429
+ "\u001b[0;31mOSError\u001b[0m Traceback (most recent call last)",
2430
+ "\u001b[0;32m<ipython-input-31-d2e90939d965>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[0;31m#trainer.train()\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0mtrainer\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtrain\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mresume_from_checkpoint\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mTrue\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
2431
+ "\u001b[0;32m~/.local/lib/python3.8/site-packages/transformers/trainer.py\u001b[0m in \u001b[0;36mtrain\u001b[0;34m(self, resume_from_checkpoint, trial, ignore_keys_for_eval, **kwargs)\u001b[0m\n\u001b[1;32m 1532\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_inner_training_loop\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_train_batch_size\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0margs\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mauto_find_batch_size\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1533\u001b[0m )\n\u001b[0;32m-> 1534\u001b[0;31m return inner_training_loop(\n\u001b[0m\u001b[1;32m 1535\u001b[0m \u001b[0margs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1536\u001b[0m \u001b[0mresume_from_checkpoint\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mresume_from_checkpoint\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
2432
+ "\u001b[0;32m~/.local/lib/python3.8/site-packages/transformers/trainer.py\u001b[0m in \u001b[0;36m_inner_training_loop\u001b[0;34m(self, batch_size, args, resume_from_checkpoint, trial, ignore_keys_for_eval)\u001b[0m\n\u001b[1;32m 1857\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcontrol\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcallback_handler\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mon_step_end\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstate\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcontrol\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1858\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1859\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_maybe_log_save_evaluate\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtr_loss\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmodel\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtrial\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mepoch\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mignore_keys_for_eval\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1860\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1861\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcontrol\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcallback_handler\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mon_substep_end\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstate\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcontrol\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
2433
+ "\u001b[0;32m~/.local/lib/python3.8/site-packages/transformers/trainer.py\u001b[0m in \u001b[0;36m_maybe_log_save_evaluate\u001b[0;34m(self, tr_loss, model, trial, epoch, ignore_keys_for_eval)\u001b[0m\n\u001b[1;32m 2124\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2125\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcontrol\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mshould_save\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2126\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_save_checkpoint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmodel\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtrial\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmetrics\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mmetrics\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 2127\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcontrol\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcallback_handler\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mon_save\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstate\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcontrol\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2128\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
2434
+ "\u001b[0;32m~/.local/lib/python3.8/site-packages/transformers/trainer.py\u001b[0m in \u001b[0;36m_save_checkpoint\u001b[0;34m(self, model, trial, metrics)\u001b[0m\n\u001b[1;32m 2268\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2269\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpush_to_hub\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2270\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_push_from_checkpoint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0moutput_dir\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 2271\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2272\u001b[0m \u001b[0;31m# Maybe delete some older checkpoints.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
2435
+ "\u001b[0;32m~/.local/lib/python3.8/site-packages/transformers/trainer.py\u001b[0m in \u001b[0;36m_push_from_checkpoint\u001b[0;34m(self, checkpoint_folder)\u001b[0m\n\u001b[1;32m 3440\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3441\u001b[0m \u001b[0mcommit_message\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34mf\"Training in progress, epoch {int(self.state.epoch)}\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 3442\u001b[0;31m _, self.push_in_progress = self.repo.push_to_hub(\n\u001b[0m\u001b[1;32m 3443\u001b[0m \u001b[0mcommit_message\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mcommit_message\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mblocking\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mFalse\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mauto_lfs_prune\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mTrue\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3444\u001b[0m )\n",
2436
+ "\u001b[0;32m~/.local/lib/python3.8/site-packages/huggingface_hub/repository.py\u001b[0m in \u001b[0;36mpush_to_hub\u001b[0;34m(self, commit_message, blocking, clean_ok, auto_lfs_prune)\u001b[0m\n\u001b[1;32m 1428\u001b[0m \u001b[0mlogger\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0minfo\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"Repo currently clean. Ignoring push_to_hub\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1429\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1430\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mgit_add\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mauto_lfs_track\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mTrue\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1431\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mgit_commit\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcommit_message\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1432\u001b[0m return self.git_push(\n",
2437
+ "\u001b[0;32m~/.local/lib/python3.8/site-packages/huggingface_hub/repository.py\u001b[0m in \u001b[0;36mgit_add\u001b[0;34m(self, pattern, auto_lfs_track)\u001b[0m\n\u001b[1;32m 1123\u001b[0m \u001b[0mlogger\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0minfo\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34mf\"Adding to index:\\n{result.stdout}\\n\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1124\u001b[0m \u001b[0;32mexcept\u001b[0m \u001b[0msubprocess\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mCalledProcessError\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mexc\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1125\u001b[0;31m \u001b[0;32mraise\u001b[0m \u001b[0mEnvironmentError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mexc\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstderr\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1126\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1127\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0mgit_commit\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcommit_message\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mstr\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m\"commit files to HF hub\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
2438
+ "\u001b[0;31mOSError\u001b[0m: error: insufficient permission for adding an object to repository database .git/objects\nerror: e5_interleaving-resume.ipynb: failed to insert into database\nerror: unable to index file 'e5_interleaving-resume.ipynb'\nfatal: adding files failed\n"
2439
+ ]
2440
  }
2441
  ],
2442
  "source": [
 
2469
  },
2470
  {
2471
  "cell_type": "code",
2472
+ "execution_count": 32,
2473
  "id": "6dd0e310-9b07-4133-ac14-2ed2d7524e22",
2474
  "metadata": {
2475
  "id": "6dd0e310-9b07-4133-ac14-2ed2d7524e22"
 
2501
  },
2502
  {
2503
  "cell_type": "code",
2504
+ "execution_count": 33,
2505
  "id": "95737cda-c5dd-4887-a4d0-dfcb0d61d977",
2506
  "metadata": {
2507
  "id": "95737cda-c5dd-4887-a4d0-dfcb0d61d977"
2508
  },
2509
+ "outputs": [
2510
+ {
2511
+ "name": "stderr",
2512
+ "output_type": "stream",
2513
+ "text": [
2514
+ "Saving model checkpoint to ./whisper-medium-el\n",
2515
+ "Configuration saved in ./whisper-medium-el/config.json\n",
2516
+ "Model weights saved in ./whisper-medium-el/pytorch_model.bin\n",
2517
+ "Feature extractor saved in ./whisper-medium-el/preprocessor_config.json\n",
2518
+ "tokenizer config file saved in ./whisper-medium-el/tokenizer_config.json\n",
2519
+ "Special tokens file saved in ./whisper-medium-el/special_tokens_map.json\n",
2520
+ "added tokens file saved in ./whisper-medium-el/added_tokens.json\n"
2521
+ ]
2522
+ },
2523
+ {
2524
+ "data": {
2525
+ "application/vnd.jupyter.widget-view+json": {
2526
+ "model_id": "2cbda43ce4ff41d5b06481239fded50f",
2527
+ "version_major": 2,
2528
+ "version_minor": 0
2529
+ },
2530
+ "text/plain": [
2531
+ "Upload file pytorch_model.bin: 0%| | 32.0k/2.85G [00:00<?, ?B/s]"
2532
+ ]
2533
+ },
2534
+ "metadata": {},
2535
+ "output_type": "display_data"
2536
+ },
2537
+ {
2538
+ "data": {
2539
+ "application/vnd.jupyter.widget-view+json": {
2540
+ "model_id": "db4ed1affb114c42b26729e11290eecb",
2541
+ "version_major": 2,
2542
+ "version_minor": 0
2543
+ },
2544
+ "text/plain": [
2545
+ "Upload file runs/Dec13_22-18-00_129-146-102-49/events.out.tfevents.1670969892.129-146-102-49.1014402.0: 100%|#…"
2546
+ ]
2547
+ },
2548
+ "metadata": {},
2549
+ "output_type": "display_data"
2550
+ },
2551
+ {
2552
+ "data": {
2553
+ "application/vnd.jupyter.widget-view+json": {
2554
+ "model_id": "100ef8c0a2fe43c5addf74c61285eaab",
2555
+ "version_major": 2,
2556
+ "version_minor": 0
2557
+ },
2558
+ "text/plain": [
2559
+ "Upload file runs/Dec14_10-24-09_129-146-102-49/events.out.tfevents.1671013461.129-146-102-49.1508853.0: 100%|#…"
2560
+ ]
2561
+ },
2562
+ "metadata": {},
2563
+ "output_type": "display_data"
2564
+ },
2565
+ {
2566
+ "data": {
2567
+ "application/vnd.jupyter.widget-view+json": {
2568
+ "model_id": "c411394dc89542228e4247cf4404cb9c",
2569
+ "version_major": 2,
2570
+ "version_minor": 0
2571
+ },
2572
+ "text/plain": [
2573
+ "Upload file runs/Dec13_21-29-08_129-146-102-49/1670966960.518305/events.out.tfevents.1670966960.129-146-102-49…"
2574
+ ]
2575
+ },
2576
+ "metadata": {},
2577
+ "output_type": "display_data"
2578
+ },
2579
+ {
2580
+ "data": {
2581
+ "application/vnd.jupyter.widget-view+json": {
2582
+ "model_id": "5a6b5004d08c44e6a4dce7eaa4554bab",
2583
+ "version_major": 2,
2584
+ "version_minor": 0
2585
+ },
2586
+ "text/plain": [
2587
+ "Upload file runs/Dec14_05-46-08_129-146-102-49/events.out.tfevents.1670996781.129-146-102-49.1113148.0: 100%|#…"
2588
+ ]
2589
+ },
2590
+ "metadata": {},
2591
+ "output_type": "display_data"
2592
+ },
2593
+ {
2594
+ "data": {
2595
+ "application/vnd.jupyter.widget-view+json": {
2596
+ "model_id": "7123410c13d54ed796907c1ecff8939a",
2597
+ "version_major": 2,
2598
+ "version_minor": 0
2599
+ },
2600
+ "text/plain": [
2601
+ "Upload file runs/Dec14_10-24-09_129-146-102-49/1671013461.8981154/events.out.tfevents.1671013461.129-146-102-4…"
2602
+ ]
2603
+ },
2604
+ "metadata": {},
2605
+ "output_type": "display_data"
2606
+ },
2607
+ {
2608
+ "data": {
2609
+ "application/vnd.jupyter.widget-view+json": {
2610
+ "model_id": "09acbed22fcb40e0891ecfdbe59ad49f",
2611
+ "version_major": 2,
2612
+ "version_minor": 0
2613
+ },
2614
+ "text/plain": [
2615
+ "Upload file runs/Dec13_22-18-00_129-146-102-49/1670995449.379962/events.out.tfevents.1670995449.129-146-102-49…"
2616
+ ]
2617
+ },
2618
+ "metadata": {},
2619
+ "output_type": "display_data"
2620
+ },
2621
+ {
2622
+ "data": {
2623
+ "application/vnd.jupyter.widget-view+json": {
2624
+ "model_id": "db66c15e43054390937cc69da7bb0ff1",
2625
+ "version_major": 2,
2626
+ "version_minor": 0
2627
+ },
2628
+ "text/plain": [
2629
+ "Upload file runs/Dec13_22-18-00_129-146-102-49/1670969892.775061/events.out.tfevents.1670969892.129-146-102-49…"
2630
+ ]
2631
+ },
2632
+ "metadata": {},
2633
+ "output_type": "display_data"
2634
+ },
2635
+ {
2636
+ "data": {
2637
+ "application/vnd.jupyter.widget-view+json": {
2638
+ "model_id": "2801f758dd794a79b48298bea97c61f9",
2639
+ "version_major": 2,
2640
+ "version_minor": 0
2641
+ },
2642
+ "text/plain": [
2643
+ "Upload file runs/Dec14_05-46-08_129-146-102-49/1670996781.2697837/events.out.tfevents.1670996781.129-146-102-4…"
2644
+ ]
2645
+ },
2646
+ "metadata": {},
2647
+ "output_type": "display_data"
2648
+ },
2649
+ {
2650
+ "data": {
2651
+ "application/vnd.jupyter.widget-view+json": {
2652
+ "model_id": "76cb9a5ef8634ed1bedb379a305467a7",
2653
+ "version_major": 2,
2654
+ "version_minor": 0
2655
+ },
2656
+ "text/plain": [
2657
+ "Upload file runs/Dec13_21-57-38_129-146-102-49/1670968669.9597044/events.out.tfevents.1670968669.129-146-102-4…"
2658
+ ]
2659
+ },
2660
+ "metadata": {},
2661
+ "output_type": "display_data"
2662
+ },
2663
+ {
2664
+ "data": {
2665
+ "application/vnd.jupyter.widget-view+json": {
2666
+ "model_id": "1c4b9b29283543d4b8a28b69f2d9cd74",
2667
+ "version_major": 2,
2668
+ "version_minor": 0
2669
+ },
2670
+ "text/plain": [
2671
+ "Upload file runs/Dec14_09-33-49_129-146-102-49/1671010439.939292/events.out.tfevents.1671010439.129-146-102-49…"
2672
+ ]
2673
+ },
2674
+ "metadata": {},
2675
+ "output_type": "display_data"
2676
+ },
2677
+ {
2678
+ "data": {
2679
+ "application/vnd.jupyter.widget-view+json": {
2680
+ "model_id": "2a6f53fab43c4c2abd90c43de74c0abc",
2681
+ "version_major": 2,
2682
+ "version_minor": 0
2683
+ },
2684
+ "text/plain": [
2685
+ "Upload file runs/Dec13_21-29-08_129-146-102-49/events.out.tfevents.1670966960.129-146-102-49.882304.0: 100%|##…"
2686
+ ]
2687
+ },
2688
+ "metadata": {},
2689
+ "output_type": "display_data"
2690
+ },
2691
+ {
2692
+ "data": {
2693
+ "application/vnd.jupyter.widget-view+json": {
2694
+ "model_id": "e1b55c4dd65f41e8b1f03fdb4810e1c2",
2695
+ "version_major": 2,
2696
+ "version_minor": 0
2697
+ },
2698
+ "text/plain": [
2699
+ "Upload file runs/Dec13_21-57-38_129-146-102-49/events.out.tfevents.1670968669.129-146-102-49.882304.2: 100%|##…"
2700
+ ]
2701
+ },
2702
+ "metadata": {},
2703
+ "output_type": "display_data"
2704
+ },
2705
+ {
2706
+ "data": {
2707
+ "application/vnd.jupyter.widget-view+json": {
2708
+ "model_id": "770a993af24b40e1a842e6df53fd6428",
2709
+ "version_major": 2,
2710
+ "version_minor": 0
2711
+ },
2712
+ "text/plain": [
2713
+ "Upload file runs/Dec14_09-33-49_129-146-102-49/events.out.tfevents.1671010439.129-146-102-49.1212260.0: 100%|#…"
2714
+ ]
2715
+ },
2716
+ "metadata": {},
2717
+ "output_type": "display_data"
2718
+ },
2719
+ {
2720
+ "data": {
2721
+ "application/vnd.jupyter.widget-view+json": {
2722
+ "model_id": "fbbe801868074b64ac6252720fdef939",
2723
+ "version_major": 2,
2724
+ "version_minor": 0
2725
+ },
2726
+ "text/plain": [
2727
+ "Upload file training_args.bin: 100%|##########| 3.56k/3.56k [00:00<?, ?B/s]"
2728
+ ]
2729
+ },
2730
+ "metadata": {},
2731
+ "output_type": "display_data"
2732
+ },
2733
+ {
2734
+ "name": "stderr",
2735
+ "output_type": "stream",
2736
+ "text": [
2737
+ "remote: Scanning LFS files for validity, may be slow... \n",
2738
+ "remote: LFS file scan complete. \n",
2739
+ "To https://huggingface.co/emilios/whisper-medium-el\n",
2740
+ " d0a02bf..d6004cb main -> main\n",
2741
+ "\n",
2742
+ "Dropping the following result as it does not have all the necessary fields:\n",
2743
+ "{'task': {'name': 'Automatic Speech Recognition', 'type': 'automatic-speech-recognition'}, 'dataset': {'name': 'Common Voice 11.0', 'type': 'mozilla-foundation/common_voice_11_0', 'config': 'el', 'split': 'test', 'args': 'el'}}\n",
2744
+ "To https://huggingface.co/emilios/whisper-medium-el\n",
2745
+ " d6004cb..0fcacdf main -> main\n",
2746
+ "\n"
2747
+ ]
2748
+ },
2749
+ {
2750
+ "data": {
2751
+ "text/plain": [
2752
+ "'https://huggingface.co/emilios/whisper-medium-el/commit/d6004cbf9a0795ad80eecbd7642d13a34329d1ca'"
2753
+ ]
2754
+ },
2755
+ "execution_count": 33,
2756
+ "metadata": {},
2757
+ "output_type": "execute_result"
2758
+ }
2759
+ ],
2760
  "source": [
2761
  "trainer.push_to_hub(**kwargs)"
2762
  ]
 
2776
  "metadata": {},
2777
  "outputs": [],
2778
  "source": []
2779
+ },
2780
+ {
2781
+ "cell_type": "code",
2782
+ "execution_count": null,
2783
+ "id": "a7ae995c-67a9-4ded-8b61-2c22d203c7a4",
2784
+ "metadata": {},
2785
+ "outputs": [],
2786
+ "source": []
2787
+ },
2788
+ {
2789
+ "cell_type": "code",
2790
+ "execution_count": null,
2791
+ "id": "2ea7a64f-17bb-44bb-9636-66bfc10ff0d0",
2792
+ "metadata": {},
2793
+ "outputs": [],
2794
+ "source": []
2795
  }
2796
  ],
2797
  "metadata": {