emilios commited on
Commit
d0a02bf
1 Parent(s): 17bae26

4000/5000 done with both dropout values at 0.05

Browse files
.ipynb_checkpoints/e5_interleaving-cl-checkpoint.ipynb ADDED
The diff for this file is too large to render. See raw diff
 
e5_interleaving-cl.ipynb CHANGED
@@ -92,8 +92,8 @@
92
  "Building dependency tree \n",
93
  "Reading state information... Done\n",
94
  "git-lfs is already the newest version (2.9.2-1).\n",
95
- "0 upgraded, 0 newly installed, 0 to remove and 155 not upgraded.\n",
96
- "Updated git hooks.\n",
97
  "Git LFS initialized.\n"
98
  ]
99
  }
@@ -120,181 +120,25 @@
120
  "output_type": "stream",
121
  "text": [
122
  "Defaulting to user installation because normal site-packages is not writeable\n",
123
- "\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
124
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
125
- "\u001b[0mRequirement already satisfied: pip in ./.local/lib/python3.8/site-packages (22.3.1)\n",
126
- "\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
127
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
128
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
129
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
130
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
131
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
132
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
133
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
134
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
135
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
136
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
137
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
138
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
139
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
140
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
141
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
142
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
143
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
144
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
145
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
146
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
147
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
148
- "\u001b[0mDefaulting to user installation because normal site-packages is not writeable\n",
149
- "\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
150
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
151
- "\u001b[0mCollecting torch\n",
152
- " Using cached torch-1.13.0-cp38-cp38-manylinux1_x86_64.whl (890.2 MB)\n",
153
- "Collecting torchaudio\n",
154
- " Using cached torchaudio-0.13.0-cp38-cp38-manylinux1_x86_64.whl (4.2 MB)\n",
155
- "Collecting torchvision\n",
156
- " Using cached torchvision-0.14.0-cp38-cp38-manylinux1_x86_64.whl (24.3 MB)\n",
157
- "Collecting nvidia-cudnn-cu11==8.5.0.96\n",
158
- " Using cached nvidia_cudnn_cu11-8.5.0.96-2-py3-none-manylinux1_x86_64.whl (557.1 MB)\n",
159
- "Collecting nvidia-cublas-cu11==11.10.3.66\n",
160
- " Using cached nvidia_cublas_cu11-11.10.3.66-py3-none-manylinux1_x86_64.whl (317.1 MB)\n",
161
- "Collecting typing-extensions\n",
162
- " Using cached typing_extensions-4.4.0-py3-none-any.whl (26 kB)\n",
163
- "Collecting nvidia-cuda-runtime-cu11==11.7.99\n",
164
- " Using cached nvidia_cuda_runtime_cu11-11.7.99-py3-none-manylinux1_x86_64.whl (849 kB)\n",
165
- "Collecting nvidia-cuda-nvrtc-cu11==11.7.99\n",
166
- " Using cached nvidia_cuda_nvrtc_cu11-11.7.99-2-py3-none-manylinux1_x86_64.whl (21.0 MB)\n",
167
- "Collecting wheel\n",
168
- " Using cached wheel-0.38.4-py3-none-any.whl (36 kB)\n",
169
- "Collecting setuptools\n",
170
- " Using cached setuptools-65.6.3-py3-none-any.whl (1.2 MB)\n",
171
- "Collecting numpy\n",
172
- " Using cached numpy-1.24.0rc2-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (17.3 MB)\n",
173
- "Collecting pillow!=8.3.*,>=5.3.0\n",
174
- " Using cached Pillow-9.3.0-cp38-cp38-manylinux_2_28_x86_64.whl (3.3 MB)\n",
175
- "Collecting requests\n",
176
- " Using cached requests-2.28.1-py3-none-any.whl (62 kB)\n",
177
- "Collecting idna<4,>=2.5\n",
178
- " Using cached idna-3.4-py3-none-any.whl (61 kB)\n",
179
- "Collecting urllib3<1.27,>=1.21.1\n",
180
- " Using cached urllib3-1.26.13-py2.py3-none-any.whl (140 kB)\n",
181
- "Collecting charset-normalizer<3,>=2\n",
182
- " Using cached charset_normalizer-2.1.1-py3-none-any.whl (39 kB)\n",
183
- "Collecting certifi>=2017.4.17\n",
184
- " Using cached certifi-2022.12.7-py3-none-any.whl (155 kB)\n",
185
- "\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
186
- "\u001b[0mInstalling collected packages: wheel, urllib3, typing-extensions, setuptools, pillow, nvidia-cuda-nvrtc-cu11, numpy, idna, charset-normalizer, certifi, requests, nvidia-cuda-runtime-cu11, nvidia-cublas-cu11, nvidia-cudnn-cu11, torch, torchvision, torchaudio\n",
187
- " Attempting uninstall: wheel\n",
188
- "\u001b[33m WARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
189
- "\u001b[0m Found existing installation: wheel 0.38.4\n",
190
- " Uninstalling wheel-0.38.4:\n",
191
- " Successfully uninstalled wheel-0.38.4\n",
192
- " Attempting uninstall: urllib3\n",
193
- "\u001b[33m WARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
194
- "\u001b[0m Found existing installation: urllib3 1.26.13\n",
195
- " Uninstalling urllib3-1.26.13:\n",
196
- " Successfully uninstalled urllib3-1.26.13\n",
197
- " Attempting uninstall: typing-extensions\n",
198
- "\u001b[33m WARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
199
- "\u001b[0m Found existing installation: typing_extensions 4.4.0\n",
200
- " Uninstalling typing_extensions-4.4.0:\n",
201
- " Successfully uninstalled typing_extensions-4.4.0\n",
202
- " Attempting uninstall: setuptools\n",
203
- "\u001b[33m WARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
204
- "\u001b[0m Found existing installation: setuptools 65.6.3\n",
205
- " Uninstalling setuptools-65.6.3:\n",
206
- " Successfully uninstalled setuptools-65.6.3\n",
207
- " Attempting uninstall: pillow\n",
208
- "\u001b[33m WARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
209
- "\u001b[0m Found existing installation: Pillow 9.3.0\n",
210
- " Uninstalling Pillow-9.3.0:\n",
211
- " Successfully uninstalled Pillow-9.3.0\n",
212
- " Attempting uninstall: nvidia-cuda-nvrtc-cu11\n",
213
- "\u001b[33m WARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
214
- "\u001b[0m Found existing installation: nvidia-cuda-nvrtc-cu11 11.7.99\n",
215
- " Uninstalling nvidia-cuda-nvrtc-cu11-11.7.99:\n",
216
- " Successfully uninstalled nvidia-cuda-nvrtc-cu11-11.7.99\n",
217
- " Attempting uninstall: numpy\n",
218
- "\u001b[33m WARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
219
- "\u001b[0m Found existing installation: numpy 1.23.5\n",
220
- " Uninstalling numpy-1.23.5:\n",
221
- " Successfully uninstalled numpy-1.23.5\n",
222
- " Attempting uninstall: idna\n",
223
- "\u001b[33m WARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
224
- "\u001b[0m Found existing installation: idna 3.4\n",
225
- " Uninstalling idna-3.4:\n",
226
- " Successfully uninstalled idna-3.4\n",
227
- " Attempting uninstall: charset-normalizer\n",
228
- "\u001b[33m WARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
229
- "\u001b[0m Found existing installation: charset-normalizer 2.1.1\n",
230
- " Uninstalling charset-normalizer-2.1.1:\n",
231
- " Successfully uninstalled charset-normalizer-2.1.1\n",
232
- " Attempting uninstall: certifi\n",
233
- "\u001b[33m WARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
234
- "\u001b[0m Found existing installation: certifi 2022.12.7\n",
235
- " Uninstalling certifi-2022.12.7:\n",
236
- " Successfully uninstalled certifi-2022.12.7\n",
237
- " Attempting uninstall: requests\n",
238
- "\u001b[33m WARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
239
- "\u001b[0m Found existing installation: requests 2.28.1\n",
240
- " Uninstalling requests-2.28.1:\n",
241
- " Successfully uninstalled requests-2.28.1\n",
242
- " Attempting uninstall: nvidia-cuda-runtime-cu11\n",
243
- "\u001b[33m WARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
244
- "\u001b[0m Found existing installation: nvidia-cuda-runtime-cu11 11.7.99\n",
245
- " Uninstalling nvidia-cuda-runtime-cu11-11.7.99:\n",
246
- " Successfully uninstalled nvidia-cuda-runtime-cu11-11.7.99\n",
247
- " Attempting uninstall: nvidia-cublas-cu11\n",
248
- "\u001b[33m WARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
249
- "\u001b[0m Found existing installation: nvidia-cublas-cu11 11.10.3.66\n",
250
- " Uninstalling nvidia-cublas-cu11-11.10.3.66:\n",
251
- " Successfully uninstalled nvidia-cublas-cu11-11.10.3.66\n",
252
- " Attempting uninstall: nvidia-cudnn-cu11\n",
253
- "\u001b[33m WARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
254
- "\u001b[0m Found existing installation: nvidia-cudnn-cu11 8.5.0.96\n",
255
- " Uninstalling nvidia-cudnn-cu11-8.5.0.96:\n",
256
- " Successfully uninstalled nvidia-cudnn-cu11-8.5.0.96\n",
257
- " Attempting uninstall: torch\n",
258
- "\u001b[33m WARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
259
- "\u001b[0m Found existing installation: torch 1.13.0\n",
260
- " Uninstalling torch-1.13.0:\n",
261
- " Successfully uninstalled torch-1.13.0\n",
262
- " Attempting uninstall: torchvision\n",
263
- "\u001b[33m WARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
264
- "\u001b[0m Found existing installation: torchvision 0.14.0\n",
265
- " Uninstalling torchvision-0.14.0:\n",
266
- " Successfully uninstalled torchvision-0.14.0\n",
267
- " Attempting uninstall: torchaudio\n",
268
- "\u001b[33m WARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
269
- "\u001b[0m Found existing installation: torchaudio 0.13.0\n",
270
- " Uninstalling torchaudio-0.13.0:\n",
271
- " Successfully uninstalled torchaudio-0.13.0\n",
272
- "\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
273
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
274
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
275
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
276
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
277
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
278
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
279
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
280
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
281
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
282
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
283
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
284
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
285
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
286
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
287
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
288
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
289
- "\u001b[0m\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n",
290
- "launchpadlib 1.10.13 requires testresources, which is not installed.\n",
291
- "pandas-profiling 3.4.0 requires numpy<1.24,>=1.16.0, but you have numpy 1.24.0rc2 which is incompatible.\n",
292
- "numba 0.56.4 requires numpy<1.24,>=1.18, but you have numpy 1.24.0rc2 which is incompatible.\u001b[0m\u001b[31m\n",
293
- "\u001b[0mSuccessfully installed certifi-2022.12.7 charset-normalizer-2.1.1 idna-3.4 numpy-1.24.0rc2 nvidia-cublas-cu11-11.10.3.66 nvidia-cuda-nvrtc-cu11-11.7.99 nvidia-cuda-runtime-cu11-11.7.99 nvidia-cudnn-cu11-8.5.0.96 pillow-9.3.0 requests-2.28.1 setuptools-65.6.3 torch-1.13.0 torchaudio-0.13.0 torchvision-0.14.0 typing-extensions-4.4.0 urllib3-1.26.13 wheel-0.38.4\n",
294
- "\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
295
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
296
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
297
- "\u001b[0m"
298
  ]
299
  }
300
  ],
@@ -304,7 +148,7 @@
304
  "!pip3 install --upgrade packaging>=20.9\n",
305
  "!pip3 install --upgrade typing-extensions>=3.7.4.3\n",
306
  "\n",
307
- "!pip3 install --pre torch torchaudio torchvision --force-reinstall\n",
308
  "\n",
309
  "#!pip3 install bitsandbytes\n",
310
  "\n",
@@ -341,7 +185,7 @@
341
  },
342
  {
343
  "cell_type": "code",
344
- "execution_count": 2,
345
  "id": "d74b38c5-a1fb-4214-b4f4-b5bf0869f169",
346
  "metadata": {
347
  "colab": {
@@ -356,7 +200,7 @@
356
  "name": "stdout",
357
  "output_type": "stream",
358
  "text": [
359
- "Mon Dec 12 18:05:43 2022 \n",
360
  "+-----------------------------------------------------------------------------+\n",
361
  "| NVIDIA-SMI 515.65.01 Driver Version: 515.65.01 CUDA Version: 11.7 |\n",
362
  "|-------------------------------+----------------------+----------------------+\n",
@@ -365,7 +209,7 @@
365
  "| | | MIG M. |\n",
366
  "|===============================+======================+======================|\n",
367
  "| 0 NVIDIA A100-SXM... On | 00000000:06:00.0 Off | 0 |\n",
368
- "| N/A 74C P0 350W / 400W | 36965MiB / 40960MiB | 100% Default |\n",
369
  "| | | Disabled |\n",
370
  "+-------------------------------+----------------------+----------------------+\n",
371
  " \n",
@@ -374,7 +218,7 @@
374
  "| GPU GI CI PID Type Process name GPU Memory |\n",
375
  "| ID ID Usage |\n",
376
  "|=============================================================================|\n",
377
- "| 0 N/A N/A 3651714 C python 36963MiB |\n",
378
  "+-----------------------------------------------------------------------------+\n"
379
  ]
380
  }
@@ -416,41 +260,42 @@
416
  "name": "stdout",
417
  "output_type": "stream",
418
  "text": [
419
- "Get:1 https://nvidia.github.io/libnvidia-container/stable/ubuntu18.04/amd64 InRelease [1484 B]\n",
420
- "Hit:2 https://nvidia.github.io/nvidia-container-runtime/stable/ubuntu18.04/amd64 InRelease\n",
421
- "Hit:3 http://security.ubuntu.com/ubuntu focal-security InRelease \n",
422
- "Hit:4 https://download.docker.com/linux/ubuntu focal InRelease \n",
423
- "Hit:5 https://packages.cloud.google.com/apt cloud-sdk InRelease \n",
424
- "Ign:6 http://ppa.launchpad.net/jonathonf/ffmpeg-4/ubuntu focal InRelease \n",
425
  "Hit:7 https://packages.microsoft.com/repos/azure-cli focal InRelease \n",
426
- "Hit:8 http://archive.ubuntu.com/ubuntu focal InRelease \n",
427
- "Hit:9 http://archive.lambdalabs.com/ubuntu focal InRelease \n",
428
- "Hit:10 https://pkg.cloudflare.com/cloudflared focal InRelease \n",
429
- "Err:11 http://ppa.launchpad.net/jonathonf/ffmpeg-4/ubuntu focal Release\n",
 
 
430
  " 404 Not Found [IP: 185.125.190.52 80]\n",
431
- "Hit:12 http://archive.ubuntu.com/ubuntu focal-updates InRelease\n",
432
- "Hit:13 http://archive.ubuntu.com/ubuntu focal-backports InRelease\n",
433
- "Hit:14 https://ppa.launchpadcontent.net/deadsnakes/ppa/ubuntu focal InRelease\n",
434
- "Reading package lists... Done \n",
435
  "E: The repository 'http://ppa.launchpad.net/jonathonf/ffmpeg-4/ubuntu focal Release' does not have a Release file.\n",
436
  "N: Updating from such a repository can't be done securely, and is therefore disabled by default.\n",
437
  "N: See apt-secure(8) manpage for repository creation and user configuration details.\n",
438
  "Hit:1 https://download.docker.com/linux/ubuntu focal InRelease\n",
439
  "Get:2 https://nvidia.github.io/libnvidia-container/stable/ubuntu18.04/amd64 InRelease [1484 B]\n",
440
- "Hit:3 http://security.ubuntu.com/ubuntu focal-security InRelease \u001b[0m\n",
441
- "Hit:4 https://nvidia.github.io/nvidia-container-runtime/stable/ubuntu18.04/amd64 InRelease\n",
442
- "Hit:5 https://packages.cloud.google.com/apt cloud-sdk InRelease \u001b[0m\n",
443
- "Ign:6 http://ppa.launchpad.net/jonathonf/ffmpeg-4/ubuntu focal InRelease \u001b[0m\u001b[33m\u001b[33m\n",
444
- "Hit:7 http://archive.ubuntu.com/ubuntu focal InRelease \u001b[0m\n",
445
- "Hit:8 https://packages.microsoft.com/repos/azure-cli focal InRelease \u001b[0m\u001b[33m\n",
446
- "Hit:9 http://archive.lambdalabs.com/ubuntu focal InRelease \u001b[0m\n",
447
  "Hit:10 https://pkg.cloudflare.com/cloudflared focal InRelease \u001b[0m\u001b[33m\n",
448
- "Hit:11 http://archive.ubuntu.com/ubuntu focal-updates InRelease \u001b[0m\n",
449
- "Hit:12 https://ppa.launchpadcontent.net/deadsnakes/ppa/ubuntu focal InRelease \n",
450
- "Err:13 http://ppa.launchpad.net/jonathonf/ffmpeg-4/ubuntu focal Release\n",
451
  " 404 Not Found [IP: 185.125.190.52 80]\n",
452
- "Hit:14 http://archive.ubuntu.com/ubuntu focal-backports InRelease\n",
453
- "Reading package lists... Done\u001b[33m\u001b[33m\u001b[33m\u001b[33m\n",
 
454
  "\u001b[1;31mE: \u001b[0mThe repository 'http://ppa.launchpad.net/jonathonf/ffmpeg-4/ubuntu focal Release' does not have a Release file.\u001b[0m\n",
455
  "\u001b[33mN: \u001b[0mUpdating from such a repository can't be done securely, and is therefore disabled by default.\u001b[0m\n",
456
  "\u001b[33mN: \u001b[0mSee apt-secure(8) manpage for repository creation and user configuration details.\u001b[0m\n",
@@ -458,7 +303,7 @@
458
  "Building dependency tree \n",
459
  "Reading state information... Done\n",
460
  "ffmpeg is already the newest version (7:4.2.7-0ubuntu0.1).\n",
461
- "0 upgraded, 0 newly installed, 0 to remove and 154 not upgraded.\n"
462
  ]
463
  }
464
  ],
@@ -500,210 +345,151 @@
500
  "output_type": "stream",
501
  "text": [
502
  "Defaulting to user installation because normal site-packages is not writeable\n",
503
- "\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
504
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
505
- "\u001b[0mCollecting git+https://github.com/huggingface/datasets\n",
506
- " Cloning https://github.com/huggingface/datasets to /tmp/pip-req-build-2byfy50h\n",
507
- " Running command git clone --filter=blob:none --quiet https://github.com/huggingface/datasets /tmp/pip-req-build-2byfy50h\n",
508
- " Resolved https://github.com/huggingface/datasets to commit 5266c81430628edc175013692f02f5f2747ff29e\n",
509
  " Installing build dependencies ... \u001b[?25ldone\n",
510
  "\u001b[?25h Getting requirements to build wheel ... \u001b[?25ldone\n",
511
  "\u001b[?25h Preparing metadata (pyproject.toml) ... \u001b[?25ldone\n",
512
- "\u001b[?25hRequirement already satisfied: xxhash in /usr/local/lib/python3.8/dist-packages (from datasets==2.7.1.dev0) (3.1.0)\n",
513
- "Requirement already satisfied: huggingface-hub<1.0.0,>=0.2.0 in /usr/local/lib/python3.8/dist-packages (from datasets==2.7.1.dev0) (0.11.1)\n",
514
- "Requirement already satisfied: multiprocess in /usr/local/lib/python3.8/dist-packages (from datasets==2.7.1.dev0) (0.70.14)\n",
515
- "Requirement already satisfied: fsspec[http]>=2021.11.1 in /usr/local/lib/python3.8/dist-packages (from datasets==2.7.1.dev0) (2022.11.0)\n",
516
  "Requirement already satisfied: packaging in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (22.0)\n",
517
- "Requirement already satisfied: responses<0.19 in /usr/local/lib/python3.8/dist-packages (from datasets==2.7.1.dev0) (0.18.0)\n",
518
- "Requirement already satisfied: tqdm>=4.62.1 in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (4.64.1)\n",
519
- "Requirement already satisfied: aiohttp in /usr/local/lib/python3.8/dist-packages (from datasets==2.7.1.dev0) (3.8.3)\n",
520
- "Requirement already satisfied: numpy>=1.17 in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (1.24.0rc2)\n",
521
  "Requirement already satisfied: pandas in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (1.5.1)\n",
522
- "Requirement already satisfied: requests>=2.19.0 in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (2.28.1)\n",
523
  "Requirement already satisfied: pyyaml>=5.1 in /usr/lib/python3/dist-packages (from datasets==2.7.1.dev0) (5.3.1)\n",
524
- "Requirement already satisfied: dill<0.3.7 in /usr/local/lib/python3.8/dist-packages (from datasets==2.7.1.dev0) (0.3.6)\n",
525
- "Requirement already satisfied: pyarrow>=6.0.0 in /usr/local/lib/python3.8/dist-packages (from datasets==2.7.1.dev0) (10.0.1)\n",
526
- "Requirement already satisfied: attrs>=17.3.0 in /usr/lib/python3/dist-packages (from aiohttp->datasets==2.7.1.dev0) (19.3.0)\n",
527
- "Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.8/dist-packages (from aiohttp->datasets==2.7.1.dev0) (1.3.1)\n",
528
- "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.8/dist-packages (from aiohttp->datasets==2.7.1.dev0) (1.3.3)\n",
529
- "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.8/dist-packages (from aiohttp->datasets==2.7.1.dev0) (6.0.3)\n",
530
- "Requirement already satisfied: async-timeout<5.0,>=4.0.0a3 in /usr/local/lib/python3.8/dist-packages (from aiohttp->datasets==2.7.1.dev0) (4.0.2)\n",
531
  "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",
532
- "Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.8/dist-packages (from aiohttp->datasets==2.7.1.dev0) (1.8.2)\n",
533
- "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",
 
 
 
 
534
  "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",
535
- "Requirement already satisfied: certifi>=2017.4.17 in ./.local/lib/python3.8/site-packages (from requests>=2.19.0->datasets==2.7.1.dev0) (2022.12.7)\n",
536
- "Requirement already satisfied: idna<4,>=2.5 in ./.local/lib/python3.8/site-packages (from requests>=2.19.0->datasets==2.7.1.dev0) (3.4)\n",
537
  "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",
538
- "Requirement already satisfied: pytz>=2020.1 in ./.local/lib/python3.8/site-packages (from pandas->datasets==2.7.1.dev0) (2022.5)\n",
539
  "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",
 
540
  "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",
541
- "\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
542
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
543
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
544
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
545
- "\u001b[0mDefaulting to user installation because normal site-packages is not writeable\n",
546
- "\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
547
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
548
- "\u001b[0mCollecting git+https://github.com/huggingface/transformers\n",
549
- " Cloning https://github.com/huggingface/transformers to /tmp/pip-req-build-rez3g9mu\n",
550
- " Running command git clone --filter=blob:none --quiet https://github.com/huggingface/transformers /tmp/pip-req-build-rez3g9mu\n",
551
- " Resolved https://github.com/huggingface/transformers to commit 799cea64ac1029d66e9e58f18bc6f47892270723\n",
552
  " Installing build dependencies ... \u001b[?25ldone\n",
553
  "\u001b[?25h Getting requirements to build wheel ... \u001b[?25ldone\n",
554
  "\u001b[?25h Preparing metadata (pyproject.toml) ... \u001b[?25ldone\n",
555
- "\u001b[?25hRequirement already satisfied: huggingface-hub<1.0,>=0.10.0 in /usr/local/lib/python3.8/dist-packages (from transformers==4.26.0.dev0) (0.11.1)\n",
556
- "Requirement already satisfied: filelock in /usr/lib/python3/dist-packages (from transformers==4.26.0.dev0) (3.0.12)\n",
557
- "Requirement already satisfied: numpy>=1.17 in ./.local/lib/python3.8/site-packages (from transformers==4.26.0.dev0) (1.24.0rc2)\n",
 
 
558
  "Requirement already satisfied: requests in ./.local/lib/python3.8/site-packages (from transformers==4.26.0.dev0) (2.28.1)\n",
 
559
  "Requirement already satisfied: tqdm>=4.27 in ./.local/lib/python3.8/site-packages (from transformers==4.26.0.dev0) (4.64.1)\n",
560
- "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.8/dist-packages (from transformers==4.26.0.dev0) (2022.10.31)\n",
561
- "Requirement already satisfied: tokenizers!=0.11.3,<0.14,>=0.11.1 in /usr/local/lib/python3.8/dist-packages (from transformers==4.26.0.dev0) (0.13.2)\n",
562
- "Requirement already satisfied: pyyaml>=5.1 in /usr/lib/python3/dist-packages (from transformers==4.26.0.dev0) (5.3.1)\n",
563
- "Requirement already satisfied: packaging>=20.0 in ./.local/lib/python3.8/site-packages (from transformers==4.26.0.dev0) (22.0)\n",
564
  "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",
565
- "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",
566
  "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",
567
- "Requirement already satisfied: idna<4,>=2.5 in ./.local/lib/python3.8/site-packages (from requests->transformers==4.26.0.dev0) (3.4)\n",
568
- "Requirement already satisfied: certifi>=2017.4.17 in ./.local/lib/python3.8/site-packages (from requests->transformers==4.26.0.dev0) (2022.12.7)\n",
569
- "\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
570
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
571
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
572
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
573
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
574
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
575
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
576
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
577
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
578
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
579
- "\u001b[0mDefaulting to user installation because normal site-packages is not writeable\n",
580
- "\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
581
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
582
- "\u001b[0mRequirement already satisfied: librosa in /usr/local/lib/python3.8/dist-packages (0.9.2)\n",
583
- "Requirement already satisfied: packaging>=20.0 in ./.local/lib/python3.8/site-packages (from librosa) (22.0)\n",
584
- "Requirement already satisfied: soundfile>=0.10.2 in /usr/local/lib/python3.8/dist-packages (from librosa) (0.11.0)\n",
585
- "Requirement already satisfied: audioread>=2.1.9 in /usr/local/lib/python3.8/dist-packages (from librosa) (3.0.0)\n",
586
- "Requirement already satisfied: resampy>=0.2.2 in /usr/local/lib/python3.8/dist-packages (from librosa) (0.4.2)\n",
587
- "Requirement already satisfied: decorator>=4.0.10 in /usr/lib/python3/dist-packages (from librosa) (4.4.2)\n",
588
- "Requirement already satisfied: pooch>=1.0 in /usr/local/lib/python3.8/dist-packages (from librosa) (1.6.0)\n",
589
- "Requirement already satisfied: numba>=0.45.1 in /usr/local/lib/python3.8/dist-packages (from librosa) (0.56.4)\n",
590
- "Requirement already satisfied: numpy>=1.17.0 in ./.local/lib/python3.8/site-packages (from librosa) (1.24.0rc2)\n",
591
  "Requirement already satisfied: joblib>=0.14 in ./.local/lib/python3.8/site-packages (from librosa) (1.2.0)\n",
592
- "Requirement already satisfied: scikit-learn>=0.19.1 in /usr/lib/python3/dist-packages (from librosa) (0.22.2.post1)\n",
593
  "Requirement already satisfied: scipy>=1.2.0 in ./.local/lib/python3.8/site-packages (from librosa) (1.9.3)\n",
 
 
 
 
 
 
 
 
 
594
  "Requirement already satisfied: importlib-metadata in ./.local/lib/python3.8/site-packages (from numba>=0.45.1->librosa) (5.0.0)\n",
595
- "Requirement already satisfied: setuptools in ./.local/lib/python3.8/site-packages (from numba>=0.45.1->librosa) (65.6.3)\n",
596
- "Collecting numpy>=1.17.0\n",
597
- " Using cached numpy-1.23.5-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (17.1 MB)\n",
598
- "Requirement already satisfied: llvmlite<0.40,>=0.39.0dev0 in /usr/local/lib/python3.8/dist-packages (from numba>=0.45.1->librosa) (0.39.1)\n",
599
  "Requirement already satisfied: appdirs>=1.3.0 in /usr/lib/python3/dist-packages (from pooch>=1.0->librosa) (1.4.3)\n",
600
  "Requirement already satisfied: requests>=2.19.0 in ./.local/lib/python3.8/site-packages (from pooch>=1.0->librosa) (2.28.1)\n",
601
  "Requirement already satisfied: cffi>=1.0 in /usr/lib/python3/dist-packages (from soundfile>=0.10.2->librosa) (1.14.0)\n",
602
- "Requirement already satisfied: idna<4,>=2.5 in ./.local/lib/python3.8/site-packages (from requests>=2.19.0->pooch>=1.0->librosa) (3.4)\n",
603
- "Requirement already satisfied: certifi>=2017.4.17 in ./.local/lib/python3.8/site-packages (from requests>=2.19.0->pooch>=1.0->librosa) (2022.12.7)\n",
604
  "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",
 
605
  "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",
 
606
  "Requirement already satisfied: zipp>=0.5 in /usr/lib/python3/dist-packages (from importlib-metadata->numba>=0.45.1->librosa) (1.0.0)\n",
607
- "\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
608
- "\u001b[0mInstalling collected packages: numpy\n",
609
- " Attempting uninstall: numpy\n",
610
- "\u001b[33m WARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
611
- "\u001b[0m Found existing installation: numpy 1.24.0rc2\n",
612
- " Uninstalling numpy-1.24.0rc2:\n",
613
- " Successfully uninstalled numpy-1.24.0rc2\n",
614
- "\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
615
- "\u001b[0mSuccessfully installed numpy-1.23.5\n",
616
- "\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
617
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
618
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
619
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
620
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
621
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
622
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
623
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
624
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
625
- "\u001b[0mDefaulting to user installation because normal site-packages is not writeable\n",
626
- "\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
627
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
628
- "\u001b[0mRequirement already satisfied: jiwer in /usr/local/lib/python3.8/dist-packages (2.5.1)\n",
629
- "Requirement already satisfied: levenshtein==0.20.2 in /usr/local/lib/python3.8/dist-packages (from jiwer) (0.20.2)\n",
630
- "Requirement already satisfied: rapidfuzz<3.0.0,>=2.3.0 in /usr/local/lib/python3.8/dist-packages (from levenshtein==0.20.2->jiwer) (2.13.5)\n",
631
- "\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
632
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
633
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
634
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
635
- "\u001b[0mDefaulting to user installation because normal site-packages is not writeable\n",
636
- "\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
637
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
638
- "\u001b[0mRequirement already satisfied: gradio in ./.local/lib/python3.8/site-packages (3.12.0)\n",
639
- "Requirement already satisfied: h11<0.13,>=0.11 in ./.local/lib/python3.8/site-packages (from gradio) (0.12.0)\n",
640
- "Requirement already satisfied: pydantic in ./.local/lib/python3.8/site-packages (from gradio) (1.10.2)\n",
641
- "Requirement already satisfied: jinja2 in ./.local/lib/python3.8/site-packages (from gradio) (3.1.2)\n",
642
  "Requirement already satisfied: markdown-it-py[linkify,plugins] in ./.local/lib/python3.8/site-packages (from gradio) (2.1.0)\n",
643
- "Requirement already satisfied: fsspec in /usr/local/lib/python3.8/dist-packages (from gradio) (2022.11.0)\n",
644
- "Requirement already satisfied: aiohttp in /usr/local/lib/python3.8/dist-packages (from gradio) (3.8.3)\n",
 
 
 
 
645
  "Requirement already satisfied: pandas in ./.local/lib/python3.8/site-packages (from gradio) (1.5.1)\n",
646
  "Requirement already satisfied: httpx in ./.local/lib/python3.8/site-packages (from gradio) (0.23.1)\n",
647
- "Requirement already satisfied: numpy in ./.local/lib/python3.8/site-packages (from gradio) (1.23.5)\n",
648
- "Requirement already satisfied: ffmpy in ./.local/lib/python3.8/site-packages (from gradio) (0.3.0)\n",
649
- "Requirement already satisfied: pycryptodome in ./.local/lib/python3.8/site-packages (from gradio) (3.16.0)\n",
650
  "Requirement already satisfied: python-multipart in ./.local/lib/python3.8/site-packages (from gradio) (0.0.5)\n",
651
- "Requirement already satisfied: websockets>=10.0 in ./.local/lib/python3.8/site-packages (from gradio) (10.4)\n",
652
- "Requirement already satisfied: pyyaml in /usr/lib/python3/dist-packages (from gradio) (5.3.1)\n",
653
- "Requirement already satisfied: matplotlib in ./.local/lib/python3.8/site-packages (from gradio) (3.5.3)\n",
654
  "Requirement already satisfied: orjson in ./.local/lib/python3.8/site-packages (from gradio) (3.8.3)\n",
655
- "Requirement already satisfied: requests in ./.local/lib/python3.8/site-packages (from gradio) (2.28.1)\n",
656
- "Requirement already satisfied: uvicorn in ./.local/lib/python3.8/site-packages (from gradio) (0.20.0)\n",
657
- "Requirement already satisfied: paramiko in ./.local/lib/python3.8/site-packages (from gradio) (2.12.0)\n",
658
  "Requirement already satisfied: pydub in ./.local/lib/python3.8/site-packages (from gradio) (0.25.1)\n",
659
- "Requirement already satisfied: fastapi in ./.local/lib/python3.8/site-packages (from gradio) (0.88.0)\n",
660
- "Requirement already satisfied: pillow in ./.local/lib/python3.8/site-packages (from gradio) (9.3.0)\n",
661
- "Requirement already satisfied: attrs>=17.3.0 in /usr/lib/python3/dist-packages (from aiohttp->gradio) (19.3.0)\n",
662
- "Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.8/dist-packages (from aiohttp->gradio) (1.3.1)\n",
663
- "Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.8/dist-packages (from aiohttp->gradio) (1.8.2)\n",
664
- "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.8/dist-packages (from aiohttp->gradio) (6.0.3)\n",
665
- "Requirement already satisfied: async-timeout<5.0,>=4.0.0a3 in /usr/local/lib/python3.8/dist-packages (from aiohttp->gradio) (4.0.2)\n",
666
  "Requirement already satisfied: charset-normalizer<3.0,>=2.0 in ./.local/lib/python3.8/site-packages (from aiohttp->gradio) (2.1.1)\n",
667
- "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.8/dist-packages (from aiohttp->gradio) (1.3.3)\n",
 
 
 
 
 
668
  "Requirement already satisfied: starlette==0.22.0 in ./.local/lib/python3.8/site-packages (from fastapi->gradio) (0.22.0)\n",
669
  "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",
670
  "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",
671
- "Requirement already satisfied: sniffio in ./.local/lib/python3.8/site-packages (from httpx->gradio) (1.3.0)\n",
672
- "Requirement already satisfied: certifi in ./.local/lib/python3.8/site-packages (from httpx->gradio) (2022.12.7)\n",
673
  "Requirement already satisfied: httpcore<0.17.0,>=0.15.0 in ./.local/lib/python3.8/site-packages (from httpx->gradio) (0.15.0)\n",
 
674
  "Requirement already satisfied: rfc3986[idna2008]<2,>=1.3 in ./.local/lib/python3.8/site-packages (from httpx->gradio) (1.5.0)\n",
 
675
  "Requirement already satisfied: MarkupSafe>=2.0 in ./.local/lib/python3.8/site-packages (from jinja2->gradio) (2.1.1)\n",
676
  "Requirement already satisfied: mdurl~=0.1 in ./.local/lib/python3.8/site-packages (from markdown-it-py[linkify,plugins]->gradio) (0.1.2)\n",
677
- "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",
678
  "Requirement already satisfied: mdit-py-plugins in ./.local/lib/python3.8/site-packages (from markdown-it-py[linkify,plugins]->gradio) (0.3.3)\n",
679
- "Requirement already satisfied: cycler>=0.10 in /usr/lib/python3/dist-packages (from matplotlib->gradio) (0.10.0)\n",
680
- "Requirement already satisfied: pyparsing>=2.2.1 in /usr/lib/python3/dist-packages (from matplotlib->gradio) (2.4.6)\n",
681
  "Requirement already satisfied: kiwisolver>=1.0.1 in /usr/lib/python3/dist-packages (from matplotlib->gradio) (1.0.1)\n",
 
682
  "Requirement already satisfied: packaging>=20.0 in ./.local/lib/python3.8/site-packages (from matplotlib->gradio) (22.0)\n",
683
  "Requirement already satisfied: python-dateutil>=2.7 in ./.local/lib/python3.8/site-packages (from matplotlib->gradio) (2.8.2)\n",
684
- "Requirement already satisfied: fonttools>=4.22.0 in ./.local/lib/python3.8/site-packages (from matplotlib->gradio) (4.38.0)\n",
685
  "Requirement already satisfied: pytz>=2020.1 in ./.local/lib/python3.8/site-packages (from pandas->gradio) (2022.5)\n",
686
- "Requirement already satisfied: pynacl>=1.0.1 in /usr/lib/python3/dist-packages (from paramiko->gradio) (1.3.0)\n",
687
- "Requirement already satisfied: cryptography>=2.5 in /usr/lib/python3/dist-packages (from paramiko->gradio) (2.8)\n",
688
  "Requirement already satisfied: six in /usr/lib/python3/dist-packages (from paramiko->gradio) (1.14.0)\n",
 
689
  "Requirement already satisfied: bcrypt>=3.1.3 in ./.local/lib/python3.8/site-packages (from paramiko->gradio) (4.0.1)\n",
690
- "Requirement already satisfied: idna<4,>=2.5 in ./.local/lib/python3.8/site-packages (from requests->gradio) (3.4)\n",
 
691
  "Requirement already satisfied: urllib3<1.27,>=1.21.1 in ./.local/lib/python3.8/site-packages (from requests->gradio) (1.26.13)\n",
692
  "Requirement already satisfied: click>=7.0 in /usr/lib/python3/dist-packages (from uvicorn->gradio) (7.0)\n",
693
  "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",
694
- "\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
695
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
696
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
697
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
698
- "\u001b[0mDefaulting to user installation because normal site-packages is not writeable\n",
699
- "\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
700
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
701
- "\u001b[0mRequirement already satisfied: more-itertools in /usr/local/lib/python3.8/dist-packages (9.0.0)\n",
702
- "\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
703
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
704
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
705
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
706
- "\u001b[0m"
707
  ]
708
  }
709
  ],
@@ -735,7 +521,7 @@
735
  },
736
  {
737
  "cell_type": "code",
738
- "execution_count": 1,
739
  "id": "dff27c76-575c-432b-8916-b1b810efef4a",
740
  "metadata": {
741
  "colab": {
@@ -768,7 +554,7 @@
768
  {
769
  "data": {
770
  "application/vnd.jupyter.widget-view+json": {
771
- "model_id": "6a2bfa275b6f4cdba66b6abdab11e859",
772
  "version_major": 2,
773
  "version_minor": 0
774
  },
@@ -850,26 +636,12 @@
850
  },
851
  {
852
  "cell_type": "code",
853
- "execution_count": 1,
854
  "id": "065a8cf7-e54f-4ac3-900e-609c80714fca",
855
  "metadata": {
856
  "id": "065a8cf7-e54f-4ac3-900e-609c80714fca"
857
  },
858
- "outputs": [
859
- {
860
- "name": "stdout",
861
- "output_type": "stream",
862
- "text": [
863
- "\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
864
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
865
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
866
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
867
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
868
- "\u001b[0m\u001b[33mWARNING: Ignoring invalid distribution -orch (/home/ubuntu/.local/lib/python3.8/site-packages)\u001b[0m\u001b[33m\n",
869
- "\u001b[0m"
870
- ]
871
- }
872
- ],
873
  "source": [
874
  "!pip3 install --upgrade numexpr>=2.7.3\n",
875
  "\n",
@@ -898,7 +670,7 @@
898
  },
899
  {
900
  "cell_type": "code",
901
- "execution_count": 2,
902
  "id": "a2787582-554f-44ce-9f38-4180a5ed6b44",
903
  "metadata": {
904
  "id": "a2787582-554f-44ce-9f38-4180a5ed6b44",
@@ -960,13 +732,22 @@
960
  },
961
  {
962
  "cell_type": "code",
963
- "execution_count": 3,
964
  "id": "qOwlctMhNmCG",
965
  "metadata": {
966
  "id": "qOwlctMhNmCG",
967
  "tags": []
968
  },
969
- "outputs": [],
 
 
 
 
 
 
 
 
 
970
  "source": [
971
  "ds = load_multiple_streaming_datasets(dataset_names, dataset_config_names=dataset_config_names, text_column_names=text_column_names, use_auth_token=True)\n",
972
  "\n"
@@ -984,12 +765,22 @@
984
  },
985
  {
986
  "cell_type": "code",
987
- "execution_count": 4,
988
  "id": "imRHJOpm4V_j",
989
  "metadata": {
990
  "id": "imRHJOpm4V_j"
991
  },
992
- "outputs": [],
 
 
 
 
 
 
 
 
 
 
993
  "source": [
994
  "from datasets import IterableDatasetDict\n",
995
  "raw_datasets = IterableDatasetDict()\n",
@@ -997,6 +788,9 @@
997
  "raw_datasets[\"train\"] = load_multiple_streaming_datasets(dataset_names, dataset_config_names=dataset_config_names, text_column_names=text_column_names, use_auth_token=True)\n",
998
  "raw_datasets[\"test\"] = load_dataset(\"mozilla-foundation/common_voice_11_0\", \"el\", split=\"test\", streaming=True, use_auth_token=True)\n",
999
  "\n",
 
 
 
1000
  "#raw_datasets[\"train\"] = load_multiple_streaming_datasets(dataset_names, \"el\", split=\"\", use_auth_token=True)\n",
1001
  "#raw_datasets[\"test\"] = load_multiple_streaming_datasets(dataset_names, \"el\", split=\"\", use_auth_token=True)\n",
1002
  "\n",
@@ -1031,7 +825,7 @@
1031
  },
1032
  {
1033
  "cell_type": "code",
1034
- "execution_count": 5,
1035
  "id": "77d9f0c5-8607-4642-a8ac-c3ab2e223ea6",
1036
  "metadata": {
1037
  "id": "77d9f0c5-8607-4642-a8ac-c3ab2e223ea6"
@@ -1066,7 +860,7 @@
1066
  },
1067
  {
1068
  "cell_type": "code",
1069
- "execution_count": 6,
1070
  "id": "ab5a13b4-9bd4-4aa0-aef2-b3de9b762988",
1071
  "metadata": {
1072
  "colab": {
@@ -1083,7 +877,7 @@
1083
  " 'sentence': Value(dtype='string', id=None)}"
1084
  ]
1085
  },
1086
- "execution_count": 6,
1087
  "metadata": {},
1088
  "output_type": "execute_result"
1089
  }
@@ -1111,7 +905,7 @@
1111
  },
1112
  {
1113
  "cell_type": "code",
1114
- "execution_count": 7,
1115
  "id": "3ab6a724-3d1e-478b-a9e9-d2f85feb6c39",
1116
  "metadata": {
1117
  "id": "3ab6a724-3d1e-478b-a9e9-d2f85feb6c39"
@@ -1135,7 +929,7 @@
1135
  },
1136
  {
1137
  "cell_type": "code",
1138
- "execution_count": 8,
1139
  "id": "d041650e-1c48-4439-87b3-5b6f4a514107",
1140
  "metadata": {
1141
  "id": "d041650e-1c48-4439-87b3-5b6f4a514107"
@@ -1145,9 +939,11 @@
1145
  "import string\n",
1146
  "import re\n",
1147
  "\n",
1148
- "do_lower_case = False\n",
1149
  "do_remove_punctuation = False\n",
1150
  "\n",
 
 
1151
  "punctuation_to_remove = string.punctuation.replace(\"'\", \"\") # don't remove apostrophes\n",
1152
  "punctuation_to_remove_regex = f\"[{''.join(punctuation_to_remove)}]\"\n",
1153
  "\n",
@@ -1171,7 +967,7 @@
1171
  },
1172
  {
1173
  "cell_type": "code",
1174
- "execution_count": 9,
1175
  "id": "c085911c-a10a-41ef-8874-306e0503e9bb",
1176
  "metadata": {
1177
  "id": "c085911c-a10a-41ef-8874-306e0503e9bb"
@@ -1212,12 +1008,34 @@
1212
  },
1213
  {
1214
  "cell_type": "code",
1215
- "execution_count": 10,
1216
  "id": "a37a7cdb-9013-427f-8de9-6a8d0e9dc684",
1217
  "metadata": {
1218
  "id": "a37a7cdb-9013-427f-8de9-6a8d0e9dc684"
1219
  },
1220
- "outputs": [],
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1221
  "source": [
1222
  "vectorized_datasets = raw_datasets.map(prepare_dataset, remove_columns=list(next(iter(raw_datasets.values())).features)).with_format(\"torch\")"
1223
  ]
@@ -1234,17 +1052,40 @@
1234
  },
1235
  {
1236
  "cell_type": "code",
1237
- "execution_count": 11,
1238
  "id": "1b145699-acfc-4b1d-93a2-a2ad3d62674c",
1239
  "metadata": {
1240
  "id": "1b145699-acfc-4b1d-93a2-a2ad3d62674c"
1241
  },
1242
- "outputs": [],
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1243
  "source": [
1244
  "vectorized_datasets[\"train\"] = vectorized_datasets[\"train\"].shuffle(\n",
1245
- " buffer_size=500,\n",
1246
  " seed=0,\n",
1247
- ")"
 
 
 
1248
  ]
1249
  },
1250
  {
@@ -1259,7 +1100,7 @@
1259
  },
1260
  {
1261
  "cell_type": "code",
1262
- "execution_count": 12,
1263
  "id": "01cb25ef-4bb0-4325-9461-f59198acadf6",
1264
  "metadata": {
1265
  "id": "01cb25ef-4bb0-4325-9461-f59198acadf6"
@@ -1284,12 +1125,27 @@
1284
  },
1285
  {
1286
  "cell_type": "code",
1287
- "execution_count": 13,
1288
  "id": "333f7f6e-6053-4d3b-8924-c733c79b82ac",
1289
  "metadata": {
1290
  "id": "333f7f6e-6053-4d3b-8924-c733c79b82ac"
1291
  },
1292
- "outputs": [],
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1293
  "source": [
1294
  "vectorized_datasets[\"train\"] = vectorized_datasets[\"train\"].filter(\n",
1295
  " is_audio_in_length_range,\n",
@@ -1364,7 +1220,7 @@
1364
  },
1365
  {
1366
  "cell_type": "code",
1367
- "execution_count": 14,
1368
  "id": "8326221e-ec13-4731-bb4e-51e5fc1486c5",
1369
  "metadata": {
1370
  "id": "8326221e-ec13-4731-bb4e-51e5fc1486c5"
@@ -1416,7 +1272,7 @@
1416
  },
1417
  {
1418
  "cell_type": "code",
1419
- "execution_count": 15,
1420
  "id": "fc834702-c0d3-4a96-b101-7b87be32bf42",
1421
  "metadata": {
1422
  "id": "fc834702-c0d3-4a96-b101-7b87be32bf42"
@@ -1449,7 +1305,7 @@
1449
  },
1450
  {
1451
  "cell_type": "code",
1452
- "execution_count": 16,
1453
  "id": "b22b4011-f31f-4b57-b684-c52332f92890",
1454
  "metadata": {
1455
  "colab": {
@@ -1500,7 +1356,7 @@
1500
  },
1501
  {
1502
  "cell_type": "code",
1503
- "execution_count": 17,
1504
  "id": "a11d1bfc-9e28-460f-a287-72d8f7bc1acb",
1505
  "metadata": {
1506
  "id": "a11d1bfc-9e28-460f-a287-72d8f7bc1acb"
@@ -1549,7 +1405,7 @@
1549
  },
1550
  {
1551
  "cell_type": "code",
1552
- "execution_count": 18,
1553
  "id": "5a10cc4b-07ec-4ebd-ac1d-7c601023594f",
1554
  "metadata": {
1555
  "colab": {
@@ -1583,7 +1439,36 @@
1583
  "id": "5a10cc4b-07ec-4ebd-ac1d-7c601023594f",
1584
  "outputId": "b6c255be-8f5e-4045-b9e0-09b8196263d1"
1585
  },
1586
- "outputs": [],
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1587
  "source": [
1588
  "from transformers import WhisperForConditionalGeneration\n",
1589
  "\n",
@@ -1605,7 +1490,7 @@
1605
  },
1606
  {
1607
  "cell_type": "code",
1608
- "execution_count": 19,
1609
  "id": "62038ba3-88ed-4fce-84db-338f50dcd04f",
1610
  "metadata": {
1611
  "id": "62038ba3-88ed-4fce-84db-338f50dcd04f"
@@ -1615,9 +1500,9 @@
1615
  "model.config.forced_decoder_ids = None\n",
1616
  "model.config.suppress_tokens = []\n",
1617
  "model.config.use_cache = False\n",
1618
- "model.config.dropout=0.1\n",
1619
- "#model.config.dropout=0.05\n",
1620
- "#model.config.dropout = model.config.attention_dropout = 0.05"
1621
  ]
1622
  },
1623
  {
@@ -1642,7 +1527,7 @@
1642
  },
1643
  {
1644
  "cell_type": "code",
1645
- "execution_count": 20,
1646
  "id": "0ae3e9af-97b7-4aa0-ae85-20b23b5bcb3a",
1647
  "metadata": {
1648
  "colab": {
@@ -1659,14 +1544,13 @@
1659
  " output_dir=\"./whisper-medium-el\", # your repo name\n",
1660
  " #output_dir=\"./whisper-small-el\", # your repo name\n",
1661
  " per_device_train_batch_size=32,\n",
1662
- " gradient_accumulation_steps=1, # increase by 2x for every 2x decrease in batch size\n",
1663
  " learning_rate=1e-5,\n",
1664
  " warmup_steps=500,\n",
1665
- " max_steps=7000,\n",
 
 
1666
  " gradient_checkpointing=True,\n",
1667
- " resume_from_checkpoint=5000,\n",
1668
- " #resume_from_checkpoint=\"checkpoint-4000\"\n",
1669
- " ignore_data_skip=True,\n",
1670
  " fp16=True,\n",
1671
  " evaluation_strategy=\"steps\",\n",
1672
  " per_device_eval_batch_size=16,\n",
@@ -1686,7 +1570,7 @@
1686
  },
1687
  {
1688
  "cell_type": "code",
1689
- "execution_count": 21,
1690
  "id": "o72eOpGzD_sK",
1691
  "metadata": {
1692
  "colab": {
@@ -1700,7 +1584,7 @@
1700
  "name": "stdout",
1701
  "output_type": "stream",
1702
  "text": [
1703
- "Tue Dec 13 00:36:23 2022 \n",
1704
  "+-----------------------------------------------------------------------------+\n",
1705
  "| NVIDIA-SMI 515.65.01 Driver Version: 515.65.01 CUDA Version: 11.7 |\n",
1706
  "|-------------------------------+----------------------+----------------------+\n",
@@ -1709,7 +1593,7 @@
1709
  "| | | MIG M. |\n",
1710
  "|===============================+======================+======================|\n",
1711
  "| 0 NVIDIA A100-SXM... On | 00000000:06:00.0 Off | 0 |\n",
1712
- "| N/A 32C P0 44W / 400W | 2MiB / 40960MiB | 0% Default |\n",
1713
  "| | | Disabled |\n",
1714
  "+-------------------------------+----------------------+----------------------+\n",
1715
  " \n",
@@ -1750,7 +1634,7 @@
1750
  },
1751
  {
1752
  "cell_type": "code",
1753
- "execution_count": 22,
1754
  "id": "3ac16b62-b3c0-4c68-8f3d-9ecf471534b2",
1755
  "metadata": {
1756
  "id": "3ac16b62-b3c0-4c68-8f3d-9ecf471534b2"
@@ -1783,7 +1667,7 @@
1783
  },
1784
  {
1785
  "cell_type": "code",
1786
- "execution_count": 23,
1787
  "id": "d546d7fe-0543-479a-b708-2ebabec19493",
1788
  "metadata": {
1789
  "colab": {
@@ -2361,7 +2245,7 @@
2361
  "name": "stderr",
2362
  "output_type": "stream",
2363
  "text": [
2364
- "/home/ubuntu/whisper-medium-el/./whisper-medium-el is already a clone of https://huggingface.co/emilios/whisper-medium-el. Make sure you pull the latest changes with `repo.git_pull()`.\n",
2365
  "max_steps is given, it will override any value given in num_train_epochs\n",
2366
  "Using cuda_amp half precision backend\n"
2367
  ]
@@ -2397,7 +2281,7 @@
2397
  },
2398
  {
2399
  "cell_type": "code",
2400
- "execution_count": null,
2401
  "id": "a1ccb9ed-cbc8-4419-91c0-651e9424b672",
2402
  "metadata": {
2403
  "id": "a1ccb9ed-cbc8-4419-91c0-651e9424b672"
@@ -2407,7 +2291,12 @@
2407
  "name": "stderr",
2408
  "output_type": "stream",
2409
  "text": [
2410
- "Configuration saved in ./whisper-medium-el/config.json\n"
 
 
 
 
 
2411
  ]
2412
  }
2413
  ],
@@ -2480,7 +2369,85 @@
2480
  "metadata": {
2481
  "id": "ee8b7b8e-1c9a-4d77-9137-1778a629e6de"
2482
  },
2483
- "outputs": [],
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2484
  "source": [
2485
  "#trainer.train()\n",
2486
  "trainer.train(resume_from_checkpoint = True)\n"
@@ -2527,8 +2494,7 @@
2527
  " \"model_name\": \"Whisper Medium El Greco\", # a 'pretty' name for your model\n",
2528
  " \"finetuned_from\": \"openai/whisper-medium\",\n",
2529
  " \"tasks\": \"automatic-speech-recognition\",\n",
2530
- " \"tags\": \"hf-asr-leaderboard\",\n",
2531
- " #\"tags\": \"hf-asr-leaderboard, whisper-medium, mozilla-foundation/common_voice_11_0, greek, whisper-event\",\n",
2532
  "}"
2533
  ]
2534
  },
@@ -2557,7 +2523,15 @@
2557
  {
2558
  "cell_type": "code",
2559
  "execution_count": null,
2560
- "id": "afa8a29a-59ab-463f-b2bf-2fbf2bae9b82",
 
 
 
 
 
 
 
 
2561
  "metadata": {},
2562
  "outputs": [],
2563
  "source": []
 
92
  "Building dependency tree \n",
93
  "Reading state information... Done\n",
94
  "git-lfs is already the newest version (2.9.2-1).\n",
95
+ "0 upgraded, 0 newly installed, 0 to remove and 156 not upgraded.\n",
96
+ "Error: Failed to call git rev-parse --git-dir: exit status 128 \n",
97
  "Git LFS initialized.\n"
98
  ]
99
  }
 
120
  "output_type": "stream",
121
  "text": [
122
  "Defaulting to user installation because normal site-packages is not writeable\n",
123
+ "Requirement already satisfied: pip in ./.local/lib/python3.8/site-packages (22.3.1)\n",
124
+ "Defaulting to user installation because normal site-packages is not writeable\n",
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: typing-extensions in ./.local/lib/python3.8/site-packages (from torch) (4.4.0)\n",
131
+ "Requirement already satisfied: nvidia-cudnn-cu11==8.5.0.96 in ./.local/lib/python3.8/site-packages (from torch) (8.5.0.96)\n",
132
+ "Requirement already satisfied: nvidia-cuda-runtime-cu11==11.7.99 in ./.local/lib/python3.8/site-packages (from torch) (11.7.99)\n",
133
+ "Requirement already satisfied: setuptools in /usr/lib/python3/dist-packages (from nvidia-cublas-cu11==11.10.3.66->torch) (45.2.0)\n",
134
+ "Requirement already satisfied: wheel in /usr/lib/python3/dist-packages (from nvidia-cublas-cu11==11.10.3.66->torch) (0.34.2)\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: urllib3<1.27,>=1.21.1 in ./.local/lib/python3.8/site-packages (from requests->torchvision) (1.26.13)\n",
139
+ "Requirement already satisfied: certifi>=2017.4.17 in /usr/lib/python3/dist-packages (from requests->torchvision) (2019.11.28)\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: charset-normalizer<3,>=2 in ./.local/lib/python3.8/site-packages (from requests->torchvision) (2.1.1)\n"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
142
  ]
143
  }
144
  ],
 
148
  "!pip3 install --upgrade packaging>=20.9\n",
149
  "!pip3 install --upgrade typing-extensions>=3.7.4.3\n",
150
  "\n",
151
+ "!pip3 install --pre torch torchaudio torchvision --upgrade\n",
152
  "\n",
153
  "#!pip3 install bitsandbytes\n",
154
  "\n",
 
185
  },
186
  {
187
  "cell_type": "code",
188
+ "execution_count": 3,
189
  "id": "d74b38c5-a1fb-4214-b4f4-b5bf0869f169",
190
  "metadata": {
191
  "colab": {
 
200
  "name": "stdout",
201
  "output_type": "stream",
202
  "text": [
203
+ "Tue Dec 13 19:10:09 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 46W / 400W | 0MiB / 40960MiB | 0% Default |\n",
213
  "| | | Disabled |\n",
214
  "+-------------------------------+----------------------+----------------------+\n",
215
  " \n",
 
218
  "| GPU GI CI PID Type Process name GPU Memory |\n",
219
  "| ID ID Usage |\n",
220
  "|=============================================================================|\n",
221
+ "| No running processes found |\n",
222
  "+-----------------------------------------------------------------------------+\n"
223
  ]
224
  }
 
260
  "name": "stdout",
261
  "output_type": "stream",
262
  "text": [
263
+ "Hit:1 https://download.docker.com/linux/ubuntu focal InRelease\n",
264
+ "Get:2 https://nvidia.github.io/libnvidia-container/stable/ubuntu18.04/amd64 InRelease [1484 B]\n",
265
+ "Hit:3 https://nvidia.github.io/nvidia-container-runtime/stable/ubuntu18.04/amd64 InRelease\n",
266
+ "Get:4 https://packages.cloud.google.com/apt cloud-sdk InRelease [6751 B] \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
+ "Get:8 https://packages.cloud.google.com/apt cloud-sdk/main amd64 Packages [368 kB]\n",
271
+ "Ign:9 http://ppa.launchpad.net/jonathonf/ffmpeg-4/ubuntu focal InRelease \n",
272
+ "Hit:10 http://archive.ubuntu.com/ubuntu focal InRelease \n",
273
+ "Hit:11 https://pkg.cloudflare.com/cloudflared focal InRelease \n",
274
+ "Get:12 http://archive.ubuntu.com/ubuntu focal-updates InRelease [114 kB] \n",
275
+ "Err:13 http://ppa.launchpad.net/jonathonf/ffmpeg-4/ubuntu focal Release \n",
276
  " 404 Not Found [IP: 185.125.190.52 80]\n",
277
+ "Hit:14 https://ppa.launchpadcontent.net/deadsnakes/ppa/ubuntu focal InRelease \n",
278
+ "Get:15 http://archive.ubuntu.com/ubuntu focal-backports InRelease [108 kB]\n",
279
+ "Reading package lists... Done \n",
 
280
  "E: The repository 'http://ppa.launchpad.net/jonathonf/ffmpeg-4/ubuntu focal Release' does not have a Release file.\n",
281
  "N: Updating from such a repository can't be done securely, and is therefore disabled by default.\n",
282
  "N: See apt-secure(8) manpage for repository creation and user configuration details.\n",
283
  "Hit:1 https://download.docker.com/linux/ubuntu focal InRelease\n",
284
  "Get:2 https://nvidia.github.io/libnvidia-container/stable/ubuntu18.04/amd64 InRelease [1484 B]\n",
285
+ "Hit:3 https://nvidia.github.io/nvidia-container-runtime/stable/ubuntu18.04/amd64 InRelease\n",
286
+ "Hit:4 http://archive.lambdalabs.com/ubuntu focal InRelease \u001b[0m\n",
287
+ "Get:5 http://security.ubuntu.com/ubuntu focal-security InRelease [114 kB] \u001b[0m\u001b[33m\n",
288
+ "Hit:6 https://packages.microsoft.com/repos/azure-cli focal InRelease \u001b[0m\u001b[33m\n",
289
+ "Hit:7 https://packages.cloud.google.com/apt cloud-sdk InRelease \u001b[0m\u001b[33m\n",
290
+ "Ign:8 http://ppa.launchpad.net/jonathonf/ffmpeg-4/ubuntu focal InRelease \u001b[0m\n",
291
+ "Hit:9 http://archive.ubuntu.com/ubuntu focal InRelease \u001b[0m\u001b[33m\n",
292
  "Hit:10 https://pkg.cloudflare.com/cloudflared focal InRelease \u001b[0m\u001b[33m\n",
293
+ "Get:11 http://archive.ubuntu.com/ubuntu focal-updates InRelease [114 kB] \u001b[0m\n",
294
+ "Err:12 http://ppa.launchpad.net/jonathonf/ffmpeg-4/ubuntu focal Release \u001b[0m\u001b[33m\u001b[33m\u001b[33m\n",
 
295
  " 404 Not Found [IP: 185.125.190.52 80]\n",
296
+ "Hit:13 https://ppa.launchpadcontent.net/deadsnakes/ppa/ubuntu focal InRelease \n",
297
+ "Get:14 http://archive.ubuntu.com/ubuntu focal-backports InRelease [108 kB]\n",
298
+ "Reading package lists... Done \u001b[0m33m\u001b[33m\u001b[33m\n",
299
  "\u001b[1;31mE: \u001b[0mThe repository 'http://ppa.launchpad.net/jonathonf/ffmpeg-4/ubuntu focal Release' does not have a Release file.\u001b[0m\n",
300
  "\u001b[33mN: \u001b[0mUpdating from such a repository can't be done securely, and is therefore disabled by default.\u001b[0m\n",
301
  "\u001b[33mN: \u001b[0mSee apt-secure(8) manpage for repository creation and user configuration details.\u001b[0m\n",
 
303
  "Building dependency tree \n",
304
  "Reading state information... Done\n",
305
  "ffmpeg is already the newest version (7:4.2.7-0ubuntu0.1).\n",
306
+ "0 upgraded, 0 newly installed, 0 to remove and 156 not upgraded.\n"
307
  ]
308
  }
309
  ],
 
345
  "output_type": "stream",
346
  "text": [
347
  "Defaulting to user installation because normal site-packages is not writeable\n",
348
+ "Collecting git+https://github.com/huggingface/datasets\n",
349
+ " Cloning https://github.com/huggingface/datasets to /tmp/pip-req-build-4yfcrkqv\n",
350
+ " Running command git clone --filter=blob:none --quiet https://github.com/huggingface/datasets /tmp/pip-req-build-4yfcrkqv\n",
351
+ " Resolved https://github.com/huggingface/datasets to commit c902456677116a081f762fa2b4aad13a0aa04d6e\n",
 
 
352
  " Installing build dependencies ... \u001b[?25ldone\n",
353
  "\u001b[?25h Getting requirements to build wheel ... \u001b[?25ldone\n",
354
  "\u001b[?25h Preparing metadata (pyproject.toml) ... \u001b[?25ldone\n",
355
+ "\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",
 
 
 
356
  "Requirement already satisfied: packaging in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (22.0)\n",
357
+ "Requirement already satisfied: xxhash in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (3.1.0)\n",
358
+ "Requirement already satisfied: aiohttp in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (3.8.3)\n",
359
+ "Requirement already satisfied: numpy>=1.17 in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (1.23.5)\n",
 
360
  "Requirement already satisfied: pandas in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (1.5.1)\n",
361
+ "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",
362
  "Requirement already satisfied: pyyaml>=5.1 in /usr/lib/python3/dist-packages (from datasets==2.7.1.dev0) (5.3.1)\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: tqdm>=4.62.1 in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (4.64.1)\n",
365
+ "Requirement already satisfied: pyarrow>=6.0.0 in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (10.0.1)\n",
366
+ "Requirement already satisfied: requests>=2.19.0 in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (2.28.1)\n",
367
+ "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",
368
+ "Requirement already satisfied: multiprocess in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (0.70.14)\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: multidict<7.0,>=4.5 in ./.local/lib/python3.8/site-packages (from aiohttp->datasets==2.7.1.dev0) (6.0.3)\n",
371
+ "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",
372
+ "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",
373
+ "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",
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: attrs>=17.3.0 in /usr/lib/python3/dist-packages (from aiohttp->datasets==2.7.1.dev0) (19.3.0)\n",
376
  "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",
377
+ "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",
378
+ "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",
379
  "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",
380
+ "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",
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: pytz>=2020.1 in ./.local/lib/python3.8/site-packages (from pandas->datasets==2.7.1.dev0) (2022.5)\n",
383
  "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",
384
+ "Defaulting to user installation because normal site-packages is not writeable\n",
385
+ "Collecting git+https://github.com/huggingface/transformers\n",
386
+ " Cloning https://github.com/huggingface/transformers to /tmp/pip-req-build-kaly439h\n",
387
+ " Running command git clone --filter=blob:none --quiet https://github.com/huggingface/transformers /tmp/pip-req-build-kaly439h\n",
388
+ " Resolved https://github.com/huggingface/transformers to commit ba9da49aa298345022f35a0b7be44ce4c72b85c2\n",
 
 
 
 
 
 
389
  " Installing build dependencies ... \u001b[?25ldone\n",
390
  "\u001b[?25h Getting requirements to build wheel ... \u001b[?25ldone\n",
391
  "\u001b[?25h Preparing metadata (pyproject.toml) ... \u001b[?25ldone\n",
392
+ "\u001b[?25hRequirement already satisfied: packaging>=20.0 in ./.local/lib/python3.8/site-packages (from transformers==4.26.0.dev0) (22.0)\n",
393
+ "Requirement already satisfied: regex!=2019.12.17 in ./.local/lib/python3.8/site-packages (from transformers==4.26.0.dev0) (2022.10.31)\n",
394
+ "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",
395
+ "Requirement already satisfied: numpy>=1.17 in ./.local/lib/python3.8/site-packages (from transformers==4.26.0.dev0) (1.23.5)\n",
396
+ "Requirement already satisfied: pyyaml>=5.1 in /usr/lib/python3/dist-packages (from transformers==4.26.0.dev0) (5.3.1)\n",
397
  "Requirement already satisfied: requests in ./.local/lib/python3.8/site-packages (from transformers==4.26.0.dev0) (2.28.1)\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: tqdm>=4.27 in ./.local/lib/python3.8/site-packages (from transformers==4.26.0.dev0) (4.64.1)\n",
400
+ "Requirement already satisfied: filelock in /usr/lib/python3/dist-packages (from transformers==4.26.0.dev0) (3.0.12)\n",
 
 
 
401
  "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",
 
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: idna<4,>=2.5 in /usr/lib/python3/dist-packages (from requests->transformers==4.26.0.dev0) (2.8)\n",
405
+ "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",
406
+ "Defaulting to user installation because normal site-packages is not writeable\n",
407
+ "Requirement already satisfied: librosa in ./.local/lib/python3.8/site-packages (0.9.2)\n",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
408
  "Requirement already satisfied: joblib>=0.14 in ./.local/lib/python3.8/site-packages (from librosa) (1.2.0)\n",
409
+ "Requirement already satisfied: decorator>=4.0.10 in /usr/lib/python3/dist-packages (from librosa) (4.4.2)\n",
410
  "Requirement already satisfied: scipy>=1.2.0 in ./.local/lib/python3.8/site-packages (from librosa) (1.9.3)\n",
411
+ "Requirement already satisfied: numba>=0.45.1 in ./.local/lib/python3.8/site-packages (from librosa) (0.56.4)\n",
412
+ "Requirement already satisfied: audioread>=2.1.9 in ./.local/lib/python3.8/site-packages (from librosa) (3.0.0)\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: packaging>=20.0 in ./.local/lib/python3.8/site-packages (from librosa) (22.0)\n",
415
+ "Requirement already satisfied: numpy>=1.17.0 in ./.local/lib/python3.8/site-packages (from librosa) (1.23.5)\n",
416
+ "Requirement already satisfied: scikit-learn>=0.19.1 in /usr/lib/python3/dist-packages (from librosa) (0.22.2.post1)\n",
417
+ "Requirement already satisfied: resampy>=0.2.2 in ./.local/lib/python3.8/site-packages (from librosa) (0.4.2)\n",
418
+ "Requirement already satisfied: soundfile>=0.10.2 in ./.local/lib/python3.8/site-packages (from librosa) (0.11.0)\n",
419
+ "Requirement already satisfied: setuptools in /usr/lib/python3/dist-packages (from numba>=0.45.1->librosa) (45.2.0)\n",
420
  "Requirement already satisfied: importlib-metadata in ./.local/lib/python3.8/site-packages (from numba>=0.45.1->librosa) (5.0.0)\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: appdirs>=1.3.0 in /usr/lib/python3/dist-packages (from pooch>=1.0->librosa) (1.4.3)\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: cffi>=1.0 in /usr/lib/python3/dist-packages (from soundfile>=0.10.2->librosa) (1.14.0)\n",
 
 
425
  "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",
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: charset-normalizer<3,>=2 in ./.local/lib/python3.8/site-packages (from requests>=2.19.0->pooch>=1.0->librosa) (2.1.1)\n",
428
+ "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",
429
  "Requirement already satisfied: zipp>=0.5 in /usr/lib/python3/dist-packages (from importlib-metadata->numba>=0.45.1->librosa) (1.0.0)\n",
430
+ "Defaulting to user installation because normal site-packages is not writeable\n",
431
+ "Requirement already satisfied: jiwer in ./.local/lib/python3.8/site-packages (2.5.1)\n",
432
+ "Requirement already satisfied: levenshtein==0.20.2 in ./.local/lib/python3.8/site-packages (from jiwer) (0.20.2)\n",
433
+ "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",
434
+ "Defaulting to user installation because normal site-packages is not writeable\n",
435
+ "Requirement already satisfied: gradio in ./.local/lib/python3.8/site-packages (3.13.0)\n",
436
+ "Requirement already satisfied: fastapi in ./.local/lib/python3.8/site-packages (from gradio) (0.88.0)\n",
437
+ "Requirement already satisfied: uvicorn in ./.local/lib/python3.8/site-packages (from gradio) (0.20.0)\n",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
438
  "Requirement already satisfied: markdown-it-py[linkify,plugins] in ./.local/lib/python3.8/site-packages (from gradio) (2.1.0)\n",
439
+ "Requirement already satisfied: pillow in /usr/lib/python3/dist-packages (from gradio) (7.0.0)\n",
440
+ "Requirement already satisfied: paramiko in ./.local/lib/python3.8/site-packages (from gradio) (2.12.0)\n",
441
+ "Requirement already satisfied: aiohttp in ./.local/lib/python3.8/site-packages (from gradio) (3.8.3)\n",
442
+ "Requirement already satisfied: matplotlib in ./.local/lib/python3.8/site-packages (from gradio) (3.5.3)\n",
443
+ "Requirement already satisfied: fsspec in ./.local/lib/python3.8/site-packages (from gradio) (2022.11.0)\n",
444
+ "Requirement already satisfied: websockets>=10.0 in ./.local/lib/python3.8/site-packages (from gradio) (10.4)\n",
445
  "Requirement already satisfied: pandas in ./.local/lib/python3.8/site-packages (from gradio) (1.5.1)\n",
446
  "Requirement already satisfied: httpx in ./.local/lib/python3.8/site-packages (from gradio) (0.23.1)\n",
 
 
 
447
  "Requirement already satisfied: python-multipart in ./.local/lib/python3.8/site-packages (from gradio) (0.0.5)\n",
448
+ "Requirement already satisfied: jinja2 in ./.local/lib/python3.8/site-packages (from gradio) (3.1.2)\n",
 
 
449
  "Requirement already satisfied: orjson in ./.local/lib/python3.8/site-packages (from gradio) (3.8.3)\n",
450
+ "Requirement already satisfied: ffmpy in ./.local/lib/python3.8/site-packages (from gradio) (0.3.0)\n",
451
+ "Requirement already satisfied: pydantic in ./.local/lib/python3.8/site-packages (from gradio) (1.10.2)\n",
 
452
  "Requirement already satisfied: pydub in ./.local/lib/python3.8/site-packages (from gradio) (0.25.1)\n",
453
+ "Requirement already satisfied: h11<0.13,>=0.11 in ./.local/lib/python3.8/site-packages (from gradio) (0.12.0)\n",
454
+ "Requirement already satisfied: pyyaml in /usr/lib/python3/dist-packages (from gradio) (5.3.1)\n",
455
+ "Requirement already satisfied: requests in ./.local/lib/python3.8/site-packages (from gradio) (2.28.1)\n",
456
+ "Requirement already satisfied: pycryptodome in ./.local/lib/python3.8/site-packages (from gradio) (3.16.0)\n",
457
+ "Requirement already satisfied: numpy in ./.local/lib/python3.8/site-packages (from gradio) (1.23.5)\n",
 
 
458
  "Requirement already satisfied: charset-normalizer<3.0,>=2.0 in ./.local/lib/python3.8/site-packages (from aiohttp->gradio) (2.1.1)\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: frozenlist>=1.1.1 in ./.local/lib/python3.8/site-packages (from aiohttp->gradio) (1.3.3)\n",
461
+ "Requirement already satisfied: attrs>=17.3.0 in /usr/lib/python3/dist-packages (from aiohttp->gradio) (19.3.0)\n",
462
+ "Requirement already satisfied: multidict<7.0,>=4.5 in ./.local/lib/python3.8/site-packages (from aiohttp->gradio) (6.0.3)\n",
463
+ "Requirement already satisfied: yarl<2.0,>=1.0 in ./.local/lib/python3.8/site-packages (from aiohttp->gradio) (1.8.2)\n",
464
+ "Requirement already satisfied: aiosignal>=1.1.2 in ./.local/lib/python3.8/site-packages (from aiohttp->gradio) (1.3.1)\n",
465
  "Requirement already satisfied: starlette==0.22.0 in ./.local/lib/python3.8/site-packages (from fastapi->gradio) (0.22.0)\n",
466
  "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",
467
  "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",
 
 
468
  "Requirement already satisfied: httpcore<0.17.0,>=0.15.0 in ./.local/lib/python3.8/site-packages (from httpx->gradio) (0.15.0)\n",
469
+ "Requirement already satisfied: certifi in /usr/lib/python3/dist-packages (from httpx->gradio) (2019.11.28)\n",
470
  "Requirement already satisfied: rfc3986[idna2008]<2,>=1.3 in ./.local/lib/python3.8/site-packages (from httpx->gradio) (1.5.0)\n",
471
+ "Requirement already satisfied: sniffio in ./.local/lib/python3.8/site-packages (from httpx->gradio) (1.3.0)\n",
472
  "Requirement already satisfied: MarkupSafe>=2.0 in ./.local/lib/python3.8/site-packages (from jinja2->gradio) (2.1.1)\n",
473
  "Requirement already satisfied: mdurl~=0.1 in ./.local/lib/python3.8/site-packages (from markdown-it-py[linkify,plugins]->gradio) (0.1.2)\n",
 
474
  "Requirement already satisfied: mdit-py-plugins in ./.local/lib/python3.8/site-packages (from markdown-it-py[linkify,plugins]->gradio) (0.3.3)\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: fonttools>=4.22.0 in ./.local/lib/python3.8/site-packages (from matplotlib->gradio) (4.38.0)\n",
477
  "Requirement already satisfied: kiwisolver>=1.0.1 in /usr/lib/python3/dist-packages (from matplotlib->gradio) (1.0.1)\n",
478
+ "Requirement already satisfied: pyparsing>=2.2.1 in /usr/lib/python3/dist-packages (from matplotlib->gradio) (2.4.6)\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: python-dateutil>=2.7 in ./.local/lib/python3.8/site-packages (from matplotlib->gradio) (2.8.2)\n",
481
+ "Requirement already satisfied: cycler>=0.10 in /usr/lib/python3/dist-packages (from matplotlib->gradio) (0.10.0)\n",
482
  "Requirement already satisfied: pytz>=2020.1 in ./.local/lib/python3.8/site-packages (from pandas->gradio) (2022.5)\n",
 
 
483
  "Requirement already satisfied: six in /usr/lib/python3/dist-packages (from paramiko->gradio) (1.14.0)\n",
484
+ "Requirement already satisfied: pynacl>=1.0.1 in /usr/lib/python3/dist-packages (from paramiko->gradio) (1.3.0)\n",
485
  "Requirement already satisfied: bcrypt>=3.1.3 in ./.local/lib/python3.8/site-packages (from paramiko->gradio) (4.0.1)\n",
486
+ "Requirement already satisfied: cryptography>=2.5 in /usr/lib/python3/dist-packages (from paramiko->gradio) (2.8)\n",
487
+ "Requirement already satisfied: idna<4,>=2.5 in /usr/lib/python3/dist-packages (from requests->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: click>=7.0 in /usr/lib/python3/dist-packages (from uvicorn->gradio) (7.0)\n",
490
  "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",
491
+ "Defaulting to user installation because normal site-packages is not writeable\n",
492
+ "Requirement already satisfied: more-itertools in /usr/lib/python3/dist-packages (4.2.0)\n"
 
 
 
 
 
 
 
 
 
 
 
493
  ]
494
  }
495
  ],
 
521
  },
522
  {
523
  "cell_type": "code",
524
+ "execution_count": 6,
525
  "id": "dff27c76-575c-432b-8916-b1b810efef4a",
526
  "metadata": {
527
  "colab": {
 
554
  {
555
  "data": {
556
  "application/vnd.jupyter.widget-view+json": {
557
+ "model_id": "1ac74505b6d84e499c03b22286c4baa9",
558
  "version_major": 2,
559
  "version_minor": 0
560
  },
 
636
  },
637
  {
638
  "cell_type": "code",
639
+ "execution_count": 7,
640
  "id": "065a8cf7-e54f-4ac3-900e-609c80714fca",
641
  "metadata": {
642
  "id": "065a8cf7-e54f-4ac3-900e-609c80714fca"
643
  },
644
+ "outputs": [],
 
 
 
 
 
 
 
 
 
 
 
 
 
 
645
  "source": [
646
  "!pip3 install --upgrade numexpr>=2.7.3\n",
647
  "\n",
 
670
  },
671
  {
672
  "cell_type": "code",
673
+ "execution_count": 8,
674
  "id": "a2787582-554f-44ce-9f38-4180a5ed6b44",
675
  "metadata": {
676
  "id": "a2787582-554f-44ce-9f38-4180a5ed6b44",
 
732
  },
733
  {
734
  "cell_type": "code",
735
+ "execution_count": 9,
736
  "id": "qOwlctMhNmCG",
737
  "metadata": {
738
  "id": "qOwlctMhNmCG",
739
  "tags": []
740
  },
741
+ "outputs": [
742
+ {
743
+ "name": "stderr",
744
+ "output_type": "stream",
745
+ "text": [
746
+ "Found cached dataset common_voice_11_0 (/home/ubuntu/.cache/huggingface/datasets/mozilla-foundation___common_voice_11_0/el/11.0.0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f)\n",
747
+ "Found cached dataset fleurs (/home/ubuntu/.cache/huggingface/datasets/google___fleurs/el_gr/2.0.0/aabb39fb29739c495517ac904e2886819b6e344702f0a5b5283cb178b087c94a)\n"
748
+ ]
749
+ }
750
+ ],
751
  "source": [
752
  "ds = load_multiple_streaming_datasets(dataset_names, dataset_config_names=dataset_config_names, text_column_names=text_column_names, use_auth_token=True)\n",
753
  "\n"
 
765
  },
766
  {
767
  "cell_type": "code",
768
+ "execution_count": 10,
769
  "id": "imRHJOpm4V_j",
770
  "metadata": {
771
  "id": "imRHJOpm4V_j"
772
  },
773
+ "outputs": [
774
+ {
775
+ "name": "stderr",
776
+ "output_type": "stream",
777
+ "text": [
778
+ "Found cached dataset common_voice_11_0 (/home/ubuntu/.cache/huggingface/datasets/mozilla-foundation___common_voice_11_0/el/11.0.0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f)\n",
779
+ "Found cached dataset fleurs (/home/ubuntu/.cache/huggingface/datasets/google___fleurs/el_gr/2.0.0/aabb39fb29739c495517ac904e2886819b6e344702f0a5b5283cb178b087c94a)\n",
780
+ "Found cached dataset common_voice_11_0 (/home/ubuntu/.cache/huggingface/datasets/mozilla-foundation___common_voice_11_0/el/11.0.0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f)\n"
781
+ ]
782
+ }
783
+ ],
784
  "source": [
785
  "from datasets import IterableDatasetDict\n",
786
  "raw_datasets = IterableDatasetDict()\n",
 
788
  "raw_datasets[\"train\"] = load_multiple_streaming_datasets(dataset_names, dataset_config_names=dataset_config_names, text_column_names=text_column_names, use_auth_token=True)\n",
789
  "raw_datasets[\"test\"] = load_dataset(\"mozilla-foundation/common_voice_11_0\", \"el\", split=\"test\", streaming=True, use_auth_token=True)\n",
790
  "\n",
791
+ "\n",
792
+ "#raw_datasets = raw_datasets.remove_columns([\"accent\", \"age\", \"client_id\", \"down_votes\", \"gender\", \"locale\", \"path\", \"segment\", \"up_votes\"])\n",
793
+ "\n",
794
  "#raw_datasets[\"train\"] = load_multiple_streaming_datasets(dataset_names, \"el\", split=\"\", use_auth_token=True)\n",
795
  "#raw_datasets[\"test\"] = load_multiple_streaming_datasets(dataset_names, \"el\", split=\"\", use_auth_token=True)\n",
796
  "\n",
 
825
  },
826
  {
827
  "cell_type": "code",
828
+ "execution_count": 11,
829
  "id": "77d9f0c5-8607-4642-a8ac-c3ab2e223ea6",
830
  "metadata": {
831
  "id": "77d9f0c5-8607-4642-a8ac-c3ab2e223ea6"
 
860
  },
861
  {
862
  "cell_type": "code",
863
+ "execution_count": 12,
864
  "id": "ab5a13b4-9bd4-4aa0-aef2-b3de9b762988",
865
  "metadata": {
866
  "colab": {
 
877
  " 'sentence': Value(dtype='string', id=None)}"
878
  ]
879
  },
880
+ "execution_count": 12,
881
  "metadata": {},
882
  "output_type": "execute_result"
883
  }
 
905
  },
906
  {
907
  "cell_type": "code",
908
+ "execution_count": 13,
909
  "id": "3ab6a724-3d1e-478b-a9e9-d2f85feb6c39",
910
  "metadata": {
911
  "id": "3ab6a724-3d1e-478b-a9e9-d2f85feb6c39"
 
929
  },
930
  {
931
  "cell_type": "code",
932
+ "execution_count": 14,
933
  "id": "d041650e-1c48-4439-87b3-5b6f4a514107",
934
  "metadata": {
935
  "id": "d041650e-1c48-4439-87b3-5b6f4a514107"
 
939
  "import string\n",
940
  "import re\n",
941
  "\n",
942
+ "do_lower_case = True\n",
943
  "do_remove_punctuation = False\n",
944
  "\n",
945
+ "#normalizer = BasicTextNormalizer()\n",
946
+ "\n",
947
  "punctuation_to_remove = string.punctuation.replace(\"'\", \"\") # don't remove apostrophes\n",
948
  "punctuation_to_remove_regex = f\"[{''.join(punctuation_to_remove)}]\"\n",
949
  "\n",
 
967
  },
968
  {
969
  "cell_type": "code",
970
+ "execution_count": 15,
971
  "id": "c085911c-a10a-41ef-8874-306e0503e9bb",
972
  "metadata": {
973
  "id": "c085911c-a10a-41ef-8874-306e0503e9bb"
 
1008
  },
1009
  {
1010
  "cell_type": "code",
1011
+ "execution_count": 16,
1012
  "id": "a37a7cdb-9013-427f-8de9-6a8d0e9dc684",
1013
  "metadata": {
1014
  "id": "a37a7cdb-9013-427f-8de9-6a8d0e9dc684"
1015
  },
1016
+ "outputs": [
1017
+ {
1018
+ "data": {
1019
+ "application/vnd.jupyter.widget-view+json": {
1020
+ "model_id": "5eb200f925f84e14bc08341ee8620fd9",
1021
+ "version_major": 2,
1022
+ "version_minor": 0
1023
+ },
1024
+ "text/plain": [
1025
+ " 0%| | 0/6430 [00:00<?, ?ex/s]"
1026
+ ]
1027
+ },
1028
+ "metadata": {},
1029
+ "output_type": "display_data"
1030
+ },
1031
+ {
1032
+ "name": "stderr",
1033
+ "output_type": "stream",
1034
+ "text": [
1035
+ "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"
1036
+ ]
1037
+ }
1038
+ ],
1039
  "source": [
1040
  "vectorized_datasets = raw_datasets.map(prepare_dataset, remove_columns=list(next(iter(raw_datasets.values())).features)).with_format(\"torch\")"
1041
  ]
 
1052
  },
1053
  {
1054
  "cell_type": "code",
1055
+ "execution_count": 24,
1056
  "id": "1b145699-acfc-4b1d-93a2-a2ad3d62674c",
1057
  "metadata": {
1058
  "id": "1b145699-acfc-4b1d-93a2-a2ad3d62674c"
1059
  },
1060
+ "outputs": [
1061
+ {
1062
+ "name": "stdout",
1063
+ "output_type": "stream",
1064
+ "text": [
1065
+ "{'input_features': tensor([[-0.8154, -0.8154, -0.8154, ..., -0.8154, -0.8154, -0.8154],\n",
1066
+ " [-0.8154, -0.8154, -0.8154, ..., -0.8154, -0.8154, -0.8154],\n",
1067
+ " [-0.8154, -0.8154, -0.8154, ..., -0.8154, -0.8154, -0.8154],\n",
1068
+ " ...,\n",
1069
+ " [-0.8154, -0.8154, -0.8154, ..., -0.8154, -0.8154, -0.8154],\n",
1070
+ " [-0.8154, -0.8154, -0.8154, ..., -0.8154, -0.8154, -0.8154],\n",
1071
+ " [-0.8154, -0.8154, -0.8154, ..., -0.8154, -0.8154, -0.8154]]), 'input_length': tensor(6.6000), 'labels': tensor([50258, 50281, 50359, 50363, 7068, 26263, 11383, 3596, 2080, 3659,\n",
1072
+ " 10073, 30599, 5691, 6744, 8828, 11658, 3371, 17321, 30320, 11383,\n",
1073
+ " 3659, 5337, 4339, 20511, 4915, 3371, 33908, 44035, 3721, 19264,\n",
1074
+ " 25090, 7597, 17928, 24841, 8385, 3835, 4903, 2080, 2805, 8385,\n",
1075
+ " 3721, 39320, 8335, 3596, 21457, 4339, 5074, 1800, 8715, 6956,\n",
1076
+ " 1800, 5958, 14836, 8385, 1800, 34079, 8385, 16946, 8066, 5733,\n",
1077
+ " 24296, 9137, 9903, 50257])}\n"
1078
+ ]
1079
+ }
1080
+ ],
1081
  "source": [
1082
  "vectorized_datasets[\"train\"] = vectorized_datasets[\"train\"].shuffle(\n",
1083
+ " #buffer_size=500,\n",
1084
  " seed=0,\n",
1085
+ ")\n",
1086
+ "\n",
1087
+ "#print(vectorized_datasets[\"train\"][0])\n",
1088
+ "#print(len(vectorized_datasets))"
1089
  ]
1090
  },
1091
  {
 
1100
  },
1101
  {
1102
  "cell_type": "code",
1103
+ "execution_count": 25,
1104
  "id": "01cb25ef-4bb0-4325-9461-f59198acadf6",
1105
  "metadata": {
1106
  "id": "01cb25ef-4bb0-4325-9461-f59198acadf6"
 
1125
  },
1126
  {
1127
  "cell_type": "code",
1128
+ "execution_count": 26,
1129
  "id": "333f7f6e-6053-4d3b-8924-c733c79b82ac",
1130
  "metadata": {
1131
  "id": "333f7f6e-6053-4d3b-8924-c733c79b82ac"
1132
  },
1133
+ "outputs": [
1134
+ {
1135
+ "data": {
1136
+ "application/vnd.jupyter.widget-view+json": {
1137
+ "model_id": "aefbdf517ed24020b4fd372739f37e5f",
1138
+ "version_major": 2,
1139
+ "version_minor": 0
1140
+ },
1141
+ "text/plain": [
1142
+ " 0%| | 0/7 [00:00<?, ?ba/s]"
1143
+ ]
1144
+ },
1145
+ "metadata": {},
1146
+ "output_type": "display_data"
1147
+ }
1148
+ ],
1149
  "source": [
1150
  "vectorized_datasets[\"train\"] = vectorized_datasets[\"train\"].filter(\n",
1151
  " is_audio_in_length_range,\n",
 
1220
  },
1221
  {
1222
  "cell_type": "code",
1223
+ "execution_count": 27,
1224
  "id": "8326221e-ec13-4731-bb4e-51e5fc1486c5",
1225
  "metadata": {
1226
  "id": "8326221e-ec13-4731-bb4e-51e5fc1486c5"
 
1272
  },
1273
  {
1274
  "cell_type": "code",
1275
+ "execution_count": 28,
1276
  "id": "fc834702-c0d3-4a96-b101-7b87be32bf42",
1277
  "metadata": {
1278
  "id": "fc834702-c0d3-4a96-b101-7b87be32bf42"
 
1305
  },
1306
  {
1307
  "cell_type": "code",
1308
+ "execution_count": 29,
1309
  "id": "b22b4011-f31f-4b57-b684-c52332f92890",
1310
  "metadata": {
1311
  "colab": {
 
1356
  },
1357
  {
1358
  "cell_type": "code",
1359
+ "execution_count": 30,
1360
  "id": "a11d1bfc-9e28-460f-a287-72d8f7bc1acb",
1361
  "metadata": {
1362
  "id": "a11d1bfc-9e28-460f-a287-72d8f7bc1acb"
 
1405
  },
1406
  {
1407
  "cell_type": "code",
1408
+ "execution_count": 31,
1409
  "id": "5a10cc4b-07ec-4ebd-ac1d-7c601023594f",
1410
  "metadata": {
1411
  "colab": {
 
1439
  "id": "5a10cc4b-07ec-4ebd-ac1d-7c601023594f",
1440
  "outputId": "b6c255be-8f5e-4045-b9e0-09b8196263d1"
1441
  },
1442
+ "outputs": [
1443
+ {
1444
+ "data": {
1445
+ "application/vnd.jupyter.widget-view+json": {
1446
+ "model_id": "27fec52020a2407fa93dd57e98de8fc9",
1447
+ "version_major": 2,
1448
+ "version_minor": 0
1449
+ },
1450
+ "text/plain": [
1451
+ "Downloading: 0%| | 0.00/1.04k [00:00<?, ?B/s]"
1452
+ ]
1453
+ },
1454
+ "metadata": {},
1455
+ "output_type": "display_data"
1456
+ },
1457
+ {
1458
+ "data": {
1459
+ "application/vnd.jupyter.widget-view+json": {
1460
+ "model_id": "f8c10225aa194c909eeb19170ac75d1f",
1461
+ "version_major": 2,
1462
+ "version_minor": 0
1463
+ },
1464
+ "text/plain": [
1465
+ "Downloading: 0%| | 0.00/3.06G [00:00<?, ?B/s]"
1466
+ ]
1467
+ },
1468
+ "metadata": {},
1469
+ "output_type": "display_data"
1470
+ }
1471
+ ],
1472
  "source": [
1473
  "from transformers import WhisperForConditionalGeneration\n",
1474
  "\n",
 
1490
  },
1491
  {
1492
  "cell_type": "code",
1493
+ "execution_count": 32,
1494
  "id": "62038ba3-88ed-4fce-84db-338f50dcd04f",
1495
  "metadata": {
1496
  "id": "62038ba3-88ed-4fce-84db-338f50dcd04f"
 
1500
  "model.config.forced_decoder_ids = None\n",
1501
  "model.config.suppress_tokens = []\n",
1502
  "model.config.use_cache = False\n",
1503
+ "\n",
1504
+ "model.config.dropout = 0.05\n",
1505
+ "model.config.attention_dropout = 0.05"
1506
  ]
1507
  },
1508
  {
 
1527
  },
1528
  {
1529
  "cell_type": "code",
1530
+ "execution_count": 33,
1531
  "id": "0ae3e9af-97b7-4aa0-ae85-20b23b5bcb3a",
1532
  "metadata": {
1533
  "colab": {
 
1544
  " output_dir=\"./whisper-medium-el\", # your repo name\n",
1545
  " #output_dir=\"./whisper-small-el\", # your repo name\n",
1546
  " per_device_train_batch_size=32,\n",
1547
+ " #gradient_accumulation_steps=1, # increase by 2x for every 2x decrease in batch size\n",
1548
  " learning_rate=1e-5,\n",
1549
  " warmup_steps=500,\n",
1550
+ " max_steps=5000,\n",
1551
+ " ignore_data_skip = True,\n",
1552
+ " #resume_from_checkpoint=\"checkpoint-4000\",\n",
1553
  " gradient_checkpointing=True,\n",
 
 
 
1554
  " fp16=True,\n",
1555
  " evaluation_strategy=\"steps\",\n",
1556
  " per_device_eval_batch_size=16,\n",
 
1570
  },
1571
  {
1572
  "cell_type": "code",
1573
+ "execution_count": 34,
1574
  "id": "o72eOpGzD_sK",
1575
  "metadata": {
1576
  "colab": {
 
1584
  "name": "stdout",
1585
  "output_type": "stream",
1586
  "text": [
1587
+ "Tue Dec 13 19:33:07 2022 \n",
1588
  "+-----------------------------------------------------------------------------+\n",
1589
  "| NVIDIA-SMI 515.65.01 Driver Version: 515.65.01 CUDA Version: 11.7 |\n",
1590
  "|-------------------------------+----------------------+----------------------+\n",
 
1593
  "| | | MIG M. |\n",
1594
  "|===============================+======================+======================|\n",
1595
  "| 0 NVIDIA A100-SXM... On | 00000000:06:00.0 Off | 0 |\n",
1596
+ "| N/A 31C P0 46W / 400W | 2MiB / 40960MiB | 0% Default |\n",
1597
  "| | | Disabled |\n",
1598
  "+-------------------------------+----------------------+----------------------+\n",
1599
  " \n",
 
1634
  },
1635
  {
1636
  "cell_type": "code",
1637
+ "execution_count": 35,
1638
  "id": "3ac16b62-b3c0-4c68-8f3d-9ecf471534b2",
1639
  "metadata": {
1640
  "id": "3ac16b62-b3c0-4c68-8f3d-9ecf471534b2"
 
1667
  },
1668
  {
1669
  "cell_type": "code",
1670
+ "execution_count": 36,
1671
  "id": "d546d7fe-0543-479a-b708-2ebabec19493",
1672
  "metadata": {
1673
  "colab": {
 
2245
  "name": "stderr",
2246
  "output_type": "stream",
2247
  "text": [
2248
+ "/home/ubuntu/./whisper-medium-el is already a clone of https://huggingface.co/emilios/whisper-medium-el. Make sure you pull the latest changes with `repo.git_pull()`.\n",
2249
  "max_steps is given, it will override any value given in num_train_epochs\n",
2250
  "Using cuda_amp half precision backend\n"
2251
  ]
 
2281
  },
2282
  {
2283
  "cell_type": "code",
2284
+ "execution_count": 37,
2285
  "id": "a1ccb9ed-cbc8-4419-91c0-651e9424b672",
2286
  "metadata": {
2287
  "id": "a1ccb9ed-cbc8-4419-91c0-651e9424b672"
 
2291
  "name": "stderr",
2292
  "output_type": "stream",
2293
  "text": [
2294
+ "Configuration saved in ./whisper-medium-el/config.json\n",
2295
+ "Model weights saved in ./whisper-medium-el/pytorch_model.bin\n",
2296
+ "Feature extractor saved in ./whisper-medium-el/preprocessor_config.json\n",
2297
+ "tokenizer config file saved in ./whisper-medium-el/tokenizer_config.json\n",
2298
+ "Special tokens file saved in ./whisper-medium-el/special_tokens_map.json\n",
2299
+ "added tokens file saved in ./whisper-medium-el/added_tokens.json\n"
2300
  ]
2301
  }
2302
  ],
 
2369
  "metadata": {
2370
  "id": "ee8b7b8e-1c9a-4d77-9137-1778a629e6de"
2371
  },
2372
+ "outputs": [
2373
+ {
2374
+ "name": "stderr",
2375
+ "output_type": "stream",
2376
+ "text": [
2377
+ "Loading model from ./whisper-medium-el/checkpoint-3000.\n",
2378
+ "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",
2379
+ "/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",
2380
+ " warnings.warn(\n",
2381
+ "***** Running training *****\n",
2382
+ " Num examples = 6428\n",
2383
+ " Num Epochs = 25\n",
2384
+ " Instantaneous batch size per device = 32\n",
2385
+ " Total train batch size (w. parallel, distributed & accumulation) = 32\n",
2386
+ " Gradient Accumulation steps = 1\n",
2387
+ " Total optimization steps = 5000\n",
2388
+ " Number of trainable parameters = 763857920\n",
2389
+ " Continuing training from checkpoint, will skip to saved global_step\n",
2390
+ " Continuing training from epoch 14\n",
2391
+ " Continuing training from global step 3000\n"
2392
+ ]
2393
+ },
2394
+ {
2395
+ "data": {
2396
+ "text/html": [
2397
+ "\n",
2398
+ " <div>\n",
2399
+ " \n",
2400
+ " <progress value='4122' max='5000' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
2401
+ " [4122/5000 1:52:06 < 1:27:52, 0.17 it/s, Epoch 19.58/25]\n",
2402
+ " </div>\n",
2403
+ " <table border=\"1\" class=\"dataframe\">\n",
2404
+ " <thead>\n",
2405
+ " <tr style=\"text-align: left;\">\n",
2406
+ " <th>Step</th>\n",
2407
+ " <th>Training Loss</th>\n",
2408
+ " <th>Validation Loss</th>\n",
2409
+ " <th>Wer</th>\n",
2410
+ " </tr>\n",
2411
+ " </thead>\n",
2412
+ " <tbody>\n",
2413
+ " <tr>\n",
2414
+ " <td>4000</td>\n",
2415
+ " <td>0.000300</td>\n",
2416
+ " <td>0.367278</td>\n",
2417
+ " <td>11.534175</td>\n",
2418
+ " </tr>\n",
2419
+ " </tbody>\n",
2420
+ "</table><p>"
2421
+ ],
2422
+ "text/plain": [
2423
+ "<IPython.core.display.HTML object>"
2424
+ ]
2425
+ },
2426
+ "metadata": {},
2427
+ "output_type": "display_data"
2428
+ },
2429
+ {
2430
+ "name": "stderr",
2431
+ "output_type": "stream",
2432
+ "text": [
2433
+ "The following columns in the evaluation set don't have a corresponding argument in `WhisperForConditionalGeneration.forward` and have been ignored: path, input_length, gender, accent, up_votes, client_id, locale, age, segment, down_votes. If path, input_length, gender, accent, up_votes, client_id, locale, age, segment, down_votes are not expected by `WhisperForConditionalGeneration.forward`, you can safely ignore this message.\n",
2434
+ "***** Running Evaluation *****\n",
2435
+ " Num examples = 1696\n",
2436
+ " Batch size = 16\n",
2437
+ "Saving model checkpoint to ./whisper-medium-el/checkpoint-4000\n",
2438
+ "Configuration saved in ./whisper-medium-el/checkpoint-4000/config.json\n",
2439
+ "Model weights saved in ./whisper-medium-el/checkpoint-4000/pytorch_model.bin\n",
2440
+ "Feature extractor saved in ./whisper-medium-el/checkpoint-4000/preprocessor_config.json\n",
2441
+ "tokenizer config file saved in ./whisper-medium-el/checkpoint-4000/tokenizer_config.json\n",
2442
+ "Special tokens file saved in ./whisper-medium-el/checkpoint-4000/special_tokens_map.json\n",
2443
+ "added tokens file saved in ./whisper-medium-el/checkpoint-4000/added_tokens.json\n",
2444
+ "Feature extractor saved in ./whisper-medium-el/preprocessor_config.json\n",
2445
+ "tokenizer config file saved in ./whisper-medium-el/tokenizer_config.json\n",
2446
+ "Special tokens file saved in ./whisper-medium-el/special_tokens_map.json\n",
2447
+ "added tokens file saved in ./whisper-medium-el/added_tokens.json\n"
2448
+ ]
2449
+ }
2450
+ ],
2451
  "source": [
2452
  "#trainer.train()\n",
2453
  "trainer.train(resume_from_checkpoint = True)\n"
 
2494
  " \"model_name\": \"Whisper Medium El Greco\", # a 'pretty' name for your model\n",
2495
  " \"finetuned_from\": \"openai/whisper-medium\",\n",
2496
  " \"tasks\": \"automatic-speech-recognition\",\n",
2497
+ " \"tags\": \"hf-asr-leaderboard, whisper-medium, mozilla-foundation/common_voice_11_0, greek, whisper-event\",\n",
 
2498
  "}"
2499
  ]
2500
  },
 
2523
  {
2524
  "cell_type": "code",
2525
  "execution_count": null,
2526
+ "id": "085a8a52-4191-4d3e-a8b2-6829d948c8b8",
2527
+ "metadata": {},
2528
+ "outputs": [],
2529
+ "source": []
2530
+ },
2531
+ {
2532
+ "cell_type": "code",
2533
+ "execution_count": null,
2534
+ "id": "82a24484-5d1a-468b-bf29-57f0a124f65e",
2535
  "metadata": {},
2536
  "outputs": [],
2537
  "source": []
runs/Dec13_19-33-07_129-146-102-49/events.out.tfevents.1670959999.129-146-102-49.783430.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c02fb15df7b21e13b871faf9275292060b1244153fb2ccd8f5f0a3fa43fb718
3
- size 10958
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c78f19741a0e88635c72d7d03f7198f15a23046ae1c94f3f847bbd818d8db0e4
3
+ size 11586