Hugging Face's logo

Spaces:
pierreguillou
/
audio-to-transcript
Running

App Files Community
pierreguillou commited on
Commit
48dfdd1
·
1 Parent(s): b6cd1d1

Upload audio_to_transcript.ipynb

Browse files
Files changed (1) hide show
  1. docs/audio_to_transcript.ipynb +1633 -0
docs/audio_to_transcript.ipynb ADDED
@@ -0,0 +1,1633 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "nbformat": 4,
3
+ "nbformat_minor": 0,
4
+ "metadata": {
5
+ "colab": {
6
+ "provenance": [],
7
+ "gpuType": "T4"
8
+ },
9
+ "kernelspec": {
10
+ "name": "python3",
11
+ "display_name": "Python 3"
12
+ },
13
+ "language_info": {
14
+ "name": "python"
15
+ },
16
+ "accelerator": "GPU",
17
+ "widgets": {
18
+ "application/vnd.jupyter.widget-state+json": {
19
+ "343b14a08a624631a28a08b7ada72068": {
20
+ "model_module": "@jupyter-widgets/controls",
21
+ "model_name": "HBoxModel",
22
+ "model_module_version": "1.5.0",
23
+ "state": {
24
+ "_dom_classes": [],
25
+ "_model_module": "@jupyter-widgets/controls",
26
+ "_model_module_version": "1.5.0",
27
+ "_model_name": "HBoxModel",
28
+ "_view_count": null,
29
+ "_view_module": "@jupyter-widgets/controls",
30
+ "_view_module_version": "1.5.0",
31
+ "_view_name": "HBoxView",
32
+ "box_style": "",
33
+ "children": [
34
+ "IPY_MODEL_2f4ca8f678714e2e9e20ae2ca0b39504",
35
+ "IPY_MODEL_6afac288fbca4db7a37d7e18ea28240a",
36
+ "IPY_MODEL_c685a989f0e0488597ecc7bf51ca850b"
37
+ ],
38
+ "layout": "IPY_MODEL_9d7c0834891940bbaf92011c504eb5ad"
39
+ }
40
+ },
41
+ "2f4ca8f678714e2e9e20ae2ca0b39504": {
42
+ "model_module": "@jupyter-widgets/controls",
43
+ "model_name": "HTMLModel",
44
+ "model_module_version": "1.5.0",
45
+ "state": {
46
+ "_dom_classes": [],
47
+ "_model_module": "@jupyter-widgets/controls",
48
+ "_model_module_version": "1.5.0",
49
+ "_model_name": "HTMLModel",
50
+ "_view_count": null,
51
+ "_view_module": "@jupyter-widgets/controls",
52
+ "_view_module_version": "1.5.0",
53
+ "_view_name": "HTMLView",
54
+ "description": "",
55
+ "description_tooltip": null,
56
+ "layout": "IPY_MODEL_2e53b75876134027a1b274684fa6cc24",
57
+ "placeholder": "​",
58
+ "style": "IPY_MODEL_ccab9f55d52b4f608ffb0cd40176eb91",
59
+ "value": "Downloading (…)37e8b/tokenizer.json: 100%"
60
+ }
61
+ },
62
+ "6afac288fbca4db7a37d7e18ea28240a": {
63
+ "model_module": "@jupyter-widgets/controls",
64
+ "model_name": "FloatProgressModel",
65
+ "model_module_version": "1.5.0",
66
+ "state": {
67
+ "_dom_classes": [],
68
+ "_model_module": "@jupyter-widgets/controls",
69
+ "_model_module_version": "1.5.0",
70
+ "_model_name": "FloatProgressModel",
71
+ "_view_count": null,
72
+ "_view_module": "@jupyter-widgets/controls",
73
+ "_view_module_version": "1.5.0",
74
+ "_view_name": "ProgressView",
75
+ "bar_style": "success",
76
+ "description": "",
77
+ "description_tooltip": null,
78
+ "layout": "IPY_MODEL_48d7a28c4f01483a8bb46a381ae17e85",
79
+ "max": 2203239,
80
+ "min": 0,
81
+ "orientation": "horizontal",
82
+ "style": "IPY_MODEL_1bab5f1a6be9419bab993bd05f72ac41",
83
+ "value": 2203239
84
+ }
85
+ },
86
+ "c685a989f0e0488597ecc7bf51ca850b": {
87
+ "model_module": "@jupyter-widgets/controls",
88
+ "model_name": "HTMLModel",
89
+ "model_module_version": "1.5.0",
90
+ "state": {
91
+ "_dom_classes": [],
92
+ "_model_module": "@jupyter-widgets/controls",
93
+ "_model_module_version": "1.5.0",
94
+ "_model_name": "HTMLModel",
95
+ "_view_count": null,
96
+ "_view_module": "@jupyter-widgets/controls",
97
+ "_view_module_version": "1.5.0",
98
+ "_view_name": "HTMLView",
99
+ "description": "",
100
+ "description_tooltip": null,
101
+ "layout": "IPY_MODEL_747d4ae8cbcc44bdbcff49bde7d14aa6",
102
+ "placeholder": "​",
103
+ "style": "IPY_MODEL_710b950a3e0449088a178950aad5a15e",
104
+ "value": " 2.20M/2.20M [00:00<00:00, 8.81MB/s]"
105
+ }
106
+ },
107
+ "9d7c0834891940bbaf92011c504eb5ad": {
108
+ "model_module": "@jupyter-widgets/base",
109
+ "model_name": "LayoutModel",
110
+ "model_module_version": "1.2.0",
111
+ "state": {
112
+ "_model_module": "@jupyter-widgets/base",
113
+ "_model_module_version": "1.2.0",
114
+ "_model_name": "LayoutModel",
115
+ "_view_count": null,
116
+ "_view_module": "@jupyter-widgets/base",
117
+ "_view_module_version": "1.2.0",
118
+ "_view_name": "LayoutView",
119
+ "align_content": null,
120
+ "align_items": null,
121
+ "align_self": null,
122
+ "border": null,
123
+ "bottom": null,
124
+ "display": null,
125
+ "flex": null,
126
+ "flex_flow": null,
127
+ "grid_area": null,
128
+ "grid_auto_columns": null,
129
+ "grid_auto_flow": null,
130
+ "grid_auto_rows": null,
131
+ "grid_column": null,
132
+ "grid_gap": null,
133
+ "grid_row": null,
134
+ "grid_template_areas": null,
135
+ "grid_template_columns": null,
136
+ "grid_template_rows": null,
137
+ "height": null,
138
+ "justify_content": null,
139
+ "justify_items": null,
140
+ "left": null,
141
+ "margin": null,
142
+ "max_height": null,
143
+ "max_width": null,
144
+ "min_height": null,
145
+ "min_width": null,
146
+ "object_fit": null,
147
+ "object_position": null,
148
+ "order": null,
149
+ "overflow": null,
150
+ "overflow_x": null,
151
+ "overflow_y": null,
152
+ "padding": null,
153
+ "right": null,
154
+ "top": null,
155
+ "visibility": null,
156
+ "width": null
157
+ }
158
+ },
159
+ "2e53b75876134027a1b274684fa6cc24": {
160
+ "model_module": "@jupyter-widgets/base",
161
+ "model_name": "LayoutModel",
162
+ "model_module_version": "1.2.0",
163
+ "state": {
164
+ "_model_module": "@jupyter-widgets/base",
165
+ "_model_module_version": "1.2.0",
166
+ "_model_name": "LayoutModel",
167
+ "_view_count": null,
168
+ "_view_module": "@jupyter-widgets/base",
169
+ "_view_module_version": "1.2.0",
170
+ "_view_name": "LayoutView",
171
+ "align_content": null,
172
+ "align_items": null,
173
+ "align_self": null,
174
+ "border": null,
175
+ "bottom": null,
176
+ "display": null,
177
+ "flex": null,
178
+ "flex_flow": null,
179
+ "grid_area": null,
180
+ "grid_auto_columns": null,
181
+ "grid_auto_flow": null,
182
+ "grid_auto_rows": null,
183
+ "grid_column": null,
184
+ "grid_gap": null,
185
+ "grid_row": null,
186
+ "grid_template_areas": null,
187
+ "grid_template_columns": null,
188
+ "grid_template_rows": null,
189
+ "height": null,
190
+ "justify_content": null,
191
+ "justify_items": null,
192
+ "left": null,
193
+ "margin": null,
194
+ "max_height": null,
195
+ "max_width": null,
196
+ "min_height": null,
197
+ "min_width": null,
198
+ "object_fit": null,
199
+ "object_position": null,
200
+ "order": null,
201
+ "overflow": null,
202
+ "overflow_x": null,
203
+ "overflow_y": null,
204
+ "padding": null,
205
+ "right": null,
206
+ "top": null,
207
+ "visibility": null,
208
+ "width": null
209
+ }
210
+ },
211
+ "ccab9f55d52b4f608ffb0cd40176eb91": {
212
+ "model_module": "@jupyter-widgets/controls",
213
+ "model_name": "DescriptionStyleModel",
214
+ "model_module_version": "1.5.0",
215
+ "state": {
216
+ "_model_module": "@jupyter-widgets/controls",
217
+ "_model_module_version": "1.5.0",
218
+ "_model_name": "DescriptionStyleModel",
219
+ "_view_count": null,
220
+ "_view_module": "@jupyter-widgets/base",
221
+ "_view_module_version": "1.2.0",
222
+ "_view_name": "StyleView",
223
+ "description_width": ""
224
+ }
225
+ },
226
+ "48d7a28c4f01483a8bb46a381ae17e85": {
227
+ "model_module": "@jupyter-widgets/base",
228
+ "model_name": "LayoutModel",
229
+ "model_module_version": "1.2.0",
230
+ "state": {
231
+ "_model_module": "@jupyter-widgets/base",
232
+ "_model_module_version": "1.2.0",
233
+ "_model_name": "LayoutModel",
234
+ "_view_count": null,
235
+ "_view_module": "@jupyter-widgets/base",
236
+ "_view_module_version": "1.2.0",
237
+ "_view_name": "LayoutView",
238
+ "align_content": null,
239
+ "align_items": null,
240
+ "align_self": null,
241
+ "border": null,
242
+ "bottom": null,
243
+ "display": null,
244
+ "flex": null,
245
+ "flex_flow": null,
246
+ "grid_area": null,
247
+ "grid_auto_columns": null,
248
+ "grid_auto_flow": null,
249
+ "grid_auto_rows": null,
250
+ "grid_column": null,
251
+ "grid_gap": null,
252
+ "grid_row": null,
253
+ "grid_template_areas": null,
254
+ "grid_template_columns": null,
255
+ "grid_template_rows": null,
256
+ "height": null,
257
+ "justify_content": null,
258
+ "justify_items": null,
259
+ "left": null,
260
+ "margin": null,
261
+ "max_height": null,
262
+ "max_width": null,
263
+ "min_height": null,
264
+ "min_width": null,
265
+ "object_fit": null,
266
+ "object_position": null,
267
+ "order": null,
268
+ "overflow": null,
269
+ "overflow_x": null,
270
+ "overflow_y": null,
271
+ "padding": null,
272
+ "right": null,
273
+ "top": null,
274
+ "visibility": null,
275
+ "width": null
276
+ }
277
+ },
278
+ "1bab5f1a6be9419bab993bd05f72ac41": {
279
+ "model_module": "@jupyter-widgets/controls",
280
+ "model_name": "ProgressStyleModel",
281
+ "model_module_version": "1.5.0",
282
+ "state": {
283
+ "_model_module": "@jupyter-widgets/controls",
284
+ "_model_module_version": "1.5.0",
285
+ "_model_name": "ProgressStyleModel",
286
+ "_view_count": null,
287
+ "_view_module": "@jupyter-widgets/base",
288
+ "_view_module_version": "1.2.0",
289
+ "_view_name": "StyleView",
290
+ "bar_color": null,
291
+ "description_width": ""
292
+ }
293
+ },
294
+ "747d4ae8cbcc44bdbcff49bde7d14aa6": {
295
+ "model_module": "@jupyter-widgets/base",
296
+ "model_name": "LayoutModel",
297
+ "model_module_version": "1.2.0",
298
+ "state": {
299
+ "_model_module": "@jupyter-widgets/base",
300
+ "_model_module_version": "1.2.0",
301
+ "_model_name": "LayoutModel",
302
+ "_view_count": null,
303
+ "_view_module": "@jupyter-widgets/base",
304
+ "_view_module_version": "1.2.0",
305
+ "_view_name": "LayoutView",
306
+ "align_content": null,
307
+ "align_items": null,
308
+ "align_self": null,
309
+ "border": null,
310
+ "bottom": null,
311
+ "display": null,
312
+ "flex": null,
313
+ "flex_flow": null,
314
+ "grid_area": null,
315
+ "grid_auto_columns": null,
316
+ "grid_auto_flow": null,
317
+ "grid_auto_rows": null,
318
+ "grid_column": null,
319
+ "grid_gap": null,
320
+ "grid_row": null,
321
+ "grid_template_areas": null,
322
+ "grid_template_columns": null,
323
+ "grid_template_rows": null,
324
+ "height": null,
325
+ "justify_content": null,
326
+ "justify_items": null,
327
+ "left": null,
328
+ "margin": null,
329
+ "max_height": null,
330
+ "max_width": null,
331
+ "min_height": null,
332
+ "min_width": null,
333
+ "object_fit": null,
334
+ "object_position": null,
335
+ "order": null,
336
+ "overflow": null,
337
+ "overflow_x": null,
338
+ "overflow_y": null,
339
+ "padding": null,
340
+ "right": null,
341
+ "top": null,
342
+ "visibility": null,
343
+ "width": null
344
+ }
345
+ },
346
+ "710b950a3e0449088a178950aad5a15e": {
347
+ "model_module": "@jupyter-widgets/controls",
348
+ "model_name": "DescriptionStyleModel",
349
+ "model_module_version": "1.5.0",
350
+ "state": {
351
+ "_model_module": "@jupyter-widgets/controls",
352
+ "_model_module_version": "1.5.0",
353
+ "_model_name": "DescriptionStyleModel",
354
+ "_view_count": null,
355
+ "_view_module": "@jupyter-widgets/base",
356
+ "_view_module_version": "1.2.0",
357
+ "_view_name": "StyleView",
358
+ "description_width": ""
359
+ }
360
+ },
361
+ "ad5dceffcb9f4525b8cb4fbbbfb67d03": {
362
+ "model_module": "@jupyter-widgets/controls",
363
+ "model_name": "HBoxModel",
364
+ "model_module_version": "1.5.0",
365
+ "state": {
366
+ "_dom_classes": [],
367
+ "_model_module": "@jupyter-widgets/controls",
368
+ "_model_module_version": "1.5.0",
369
+ "_model_name": "HBoxModel",
370
+ "_view_count": null,
371
+ "_view_module": "@jupyter-widgets/controls",
372
+ "_view_module_version": "1.5.0",
373
+ "_view_name": "HBoxView",
374
+ "box_style": "",
375
+ "children": [
376
+ "IPY_MODEL_6c92704bacd2407382d3a00496297455",
377
+ "IPY_MODEL_0c466ba4c4334d759313e8be7546735a",
378
+ "IPY_MODEL_9c0f8ee844cb4ba4bd0b27bab5bc5907"
379
+ ],
380
+ "layout": "IPY_MODEL_6a3dbb4e72ce41d691dcefc4c234ae54"
381
+ }
382
+ },
383
+ "6c92704bacd2407382d3a00496297455": {
384
+ "model_module": "@jupyter-widgets/controls",
385
+ "model_name": "HTMLModel",
386
+ "model_module_version": "1.5.0",
387
+ "state": {
388
+ "_dom_classes": [],
389
+ "_model_module": "@jupyter-widgets/controls",
390
+ "_model_module_version": "1.5.0",
391
+ "_model_name": "HTMLModel",
392
+ "_view_count": null,
393
+ "_view_module": "@jupyter-widgets/controls",
394
+ "_view_module_version": "1.5.0",
395
+ "_view_name": "HTMLView",
396
+ "description": "",
397
+ "description_tooltip": null,
398
+ "layout": "IPY_MODEL_4d20f630401641f1b0bbf9aff2b8455b",
399
+ "placeholder": "​",
400
+ "style": "IPY_MODEL_3ae150cecd064383bf1ae4da4d8ab510",
401
+ "value": "Downloading (…)08837e8b/config.json: 100%"
402
+ }
403
+ },
404
+ "0c466ba4c4334d759313e8be7546735a": {
405
+ "model_module": "@jupyter-widgets/controls",
406
+ "model_name": "FloatProgressModel",
407
+ "model_module_version": "1.5.0",
408
+ "state": {
409
+ "_dom_classes": [],
410
+ "_model_module": "@jupyter-widgets/controls",
411
+ "_model_module_version": "1.5.0",
412
+ "_model_name": "FloatProgressModel",
413
+ "_view_count": null,
414
+ "_view_module": "@jupyter-widgets/controls",
415
+ "_view_module_version": "1.5.0",
416
+ "_view_name": "ProgressView",
417
+ "bar_style": "success",
418
+ "description": "",
419
+ "description_tooltip": null,
420
+ "layout": "IPY_MODEL_16e447b778734c6c8d75f2a571a2a146",
421
+ "max": 2796,
422
+ "min": 0,
423
+ "orientation": "horizontal",
424
+ "style": "IPY_MODEL_258e0ebf77fd4fd69feb43cca675b204",
425
+ "value": 2796
426
+ }
427
+ },
428
+ "9c0f8ee844cb4ba4bd0b27bab5bc5907": {
429
+ "model_module": "@jupyter-widgets/controls",
430
+ "model_name": "HTMLModel",
431
+ "model_module_version": "1.5.0",
432
+ "state": {
433
+ "_dom_classes": [],
434
+ "_model_module": "@jupyter-widgets/controls",
435
+ "_model_module_version": "1.5.0",
436
+ "_model_name": "HTMLModel",
437
+ "_view_count": null,
438
+ "_view_module": "@jupyter-widgets/controls",
439
+ "_view_module_version": "1.5.0",
440
+ "_view_name": "HTMLView",
441
+ "description": "",
442
+ "description_tooltip": null,
443
+ "layout": "IPY_MODEL_2b7fbccaeec94dee85b4e943ebada9f6",
444
+ "placeholder": "​",
445
+ "style": "IPY_MODEL_77ce76d5979d41478f2af0c80df8d7ed",
446
+ "value": " 2.80k/2.80k [00:00<00:00, 49.4kB/s]"
447
+ }
448
+ },
449
+ "6a3dbb4e72ce41d691dcefc4c234ae54": {
450
+ "model_module": "@jupyter-widgets/base",
451
+ "model_name": "LayoutModel",
452
+ "model_module_version": "1.2.0",
453
+ "state": {
454
+ "_model_module": "@jupyter-widgets/base",
455
+ "_model_module_version": "1.2.0",
456
+ "_model_name": "LayoutModel",
457
+ "_view_count": null,
458
+ "_view_module": "@jupyter-widgets/base",
459
+ "_view_module_version": "1.2.0",
460
+ "_view_name": "LayoutView",
461
+ "align_content": null,
462
+ "align_items": null,
463
+ "align_self": null,
464
+ "border": null,
465
+ "bottom": null,
466
+ "display": null,
467
+ "flex": null,
468
+ "flex_flow": null,
469
+ "grid_area": null,
470
+ "grid_auto_columns": null,
471
+ "grid_auto_flow": null,
472
+ "grid_auto_rows": null,
473
+ "grid_column": null,
474
+ "grid_gap": null,
475
+ "grid_row": null,
476
+ "grid_template_areas": null,
477
+ "grid_template_columns": null,
478
+ "grid_template_rows": null,
479
+ "height": null,
480
+ "justify_content": null,
481
+ "justify_items": null,
482
+ "left": null,
483
+ "margin": null,
484
+ "max_height": null,
485
+ "max_width": null,
486
+ "min_height": null,
487
+ "min_width": null,
488
+ "object_fit": null,
489
+ "object_position": null,
490
+ "order": null,
491
+ "overflow": null,
492
+ "overflow_x": null,
493
+ "overflow_y": null,
494
+ "padding": null,
495
+ "right": null,
496
+ "top": null,
497
+ "visibility": null,
498
+ "width": null
499
+ }
500
+ },
501
+ "4d20f630401641f1b0bbf9aff2b8455b": {
502
+ "model_module": "@jupyter-widgets/base",
503
+ "model_name": "LayoutModel",
504
+ "model_module_version": "1.2.0",
505
+ "state": {
506
+ "_model_module": "@jupyter-widgets/base",
507
+ "_model_module_version": "1.2.0",
508
+ "_model_name": "LayoutModel",
509
+ "_view_count": null,
510
+ "_view_module": "@jupyter-widgets/base",
511
+ "_view_module_version": "1.2.0",
512
+ "_view_name": "LayoutView",
513
+ "align_content": null,
514
+ "align_items": null,
515
+ "align_self": null,
516
+ "border": null,
517
+ "bottom": null,
518
+ "display": null,
519
+ "flex": null,
520
+ "flex_flow": null,
521
+ "grid_area": null,
522
+ "grid_auto_columns": null,
523
+ "grid_auto_flow": null,
524
+ "grid_auto_rows": null,
525
+ "grid_column": null,
526
+ "grid_gap": null,
527
+ "grid_row": null,
528
+ "grid_template_areas": null,
529
+ "grid_template_columns": null,
530
+ "grid_template_rows": null,
531
+ "height": null,
532
+ "justify_content": null,
533
+ "justify_items": null,
534
+ "left": null,
535
+ "margin": null,
536
+ "max_height": null,
537
+ "max_width": null,
538
+ "min_height": null,
539
+ "min_width": null,
540
+ "object_fit": null,
541
+ "object_position": null,
542
+ "order": null,
543
+ "overflow": null,
544
+ "overflow_x": null,
545
+ "overflow_y": null,
546
+ "padding": null,
547
+ "right": null,
548
+ "top": null,
549
+ "visibility": null,
550
+ "width": null
551
+ }
552
+ },
553
+ "3ae150cecd064383bf1ae4da4d8ab510": {
554
+ "model_module": "@jupyter-widgets/controls",
555
+ "model_name": "DescriptionStyleModel",
556
+ "model_module_version": "1.5.0",
557
+ "state": {
558
+ "_model_module": "@jupyter-widgets/controls",
559
+ "_model_module_version": "1.5.0",
560
+ "_model_name": "DescriptionStyleModel",
561
+ "_view_count": null,
562
+ "_view_module": "@jupyter-widgets/base",
563
+ "_view_module_version": "1.2.0",
564
+ "_view_name": "StyleView",
565
+ "description_width": ""
566
+ }
567
+ },
568
+ "16e447b778734c6c8d75f2a571a2a146": {
569
+ "model_module": "@jupyter-widgets/base",
570
+ "model_name": "LayoutModel",
571
+ "model_module_version": "1.2.0",
572
+ "state": {
573
+ "_model_module": "@jupyter-widgets/base",
574
+ "_model_module_version": "1.2.0",
575
+ "_model_name": "LayoutModel",
576
+ "_view_count": null,
577
+ "_view_module": "@jupyter-widgets/base",
578
+ "_view_module_version": "1.2.0",
579
+ "_view_name": "LayoutView",
580
+ "align_content": null,
581
+ "align_items": null,
582
+ "align_self": null,
583
+ "border": null,
584
+ "bottom": null,
585
+ "display": null,
586
+ "flex": null,
587
+ "flex_flow": null,
588
+ "grid_area": null,
589
+ "grid_auto_columns": null,
590
+ "grid_auto_flow": null,
591
+ "grid_auto_rows": null,
592
+ "grid_column": null,
593
+ "grid_gap": null,
594
+ "grid_row": null,
595
+ "grid_template_areas": null,
596
+ "grid_template_columns": null,
597
+ "grid_template_rows": null,
598
+ "height": null,
599
+ "justify_content": null,
600
+ "justify_items": null,
601
+ "left": null,
602
+ "margin": null,
603
+ "max_height": null,
604
+ "max_width": null,
605
+ "min_height": null,
606
+ "min_width": null,
607
+ "object_fit": null,
608
+ "object_position": null,
609
+ "order": null,
610
+ "overflow": null,
611
+ "overflow_x": null,
612
+ "overflow_y": null,
613
+ "padding": null,
614
+ "right": null,
615
+ "top": null,
616
+ "visibility": null,
617
+ "width": null
618
+ }
619
+ },
620
+ "258e0ebf77fd4fd69feb43cca675b204": {
621
+ "model_module": "@jupyter-widgets/controls",
622
+ "model_name": "ProgressStyleModel",
623
+ "model_module_version": "1.5.0",
624
+ "state": {
625
+ "_model_module": "@jupyter-widgets/controls",
626
+ "_model_module_version": "1.5.0",
627
+ "_model_name": "ProgressStyleModel",
628
+ "_view_count": null,
629
+ "_view_module": "@jupyter-widgets/base",
630
+ "_view_module_version": "1.2.0",
631
+ "_view_name": "StyleView",
632
+ "bar_color": null,
633
+ "description_width": ""
634
+ }
635
+ },
636
+ "2b7fbccaeec94dee85b4e943ebada9f6": {
637
+ "model_module": "@jupyter-widgets/base",
638
+ "model_name": "LayoutModel",
639
+ "model_module_version": "1.2.0",
640
+ "state": {
641
+ "_model_module": "@jupyter-widgets/base",
642
+ "_model_module_version": "1.2.0",
643
+ "_model_name": "LayoutModel",
644
+ "_view_count": null,
645
+ "_view_module": "@jupyter-widgets/base",
646
+ "_view_module_version": "1.2.0",
647
+ "_view_name": "LayoutView",
648
+ "align_content": null,
649
+ "align_items": null,
650
+ "align_self": null,
651
+ "border": null,
652
+ "bottom": null,
653
+ "display": null,
654
+ "flex": null,
655
+ "flex_flow": null,
656
+ "grid_area": null,
657
+ "grid_auto_columns": null,
658
+ "grid_auto_flow": null,
659
+ "grid_auto_rows": null,
660
+ "grid_column": null,
661
+ "grid_gap": null,
662
+ "grid_row": null,
663
+ "grid_template_areas": null,
664
+ "grid_template_columns": null,
665
+ "grid_template_rows": null,
666
+ "height": null,
667
+ "justify_content": null,
668
+ "justify_items": null,
669
+ "left": null,
670
+ "margin": null,
671
+ "max_height": null,
672
+ "max_width": null,
673
+ "min_height": null,
674
+ "min_width": null,
675
+ "object_fit": null,
676
+ "object_position": null,
677
+ "order": null,
678
+ "overflow": null,
679
+ "overflow_x": null,
680
+ "overflow_y": null,
681
+ "padding": null,
682
+ "right": null,
683
+ "top": null,
684
+ "visibility": null,
685
+ "width": null
686
+ }
687
+ },
688
+ "77ce76d5979d41478f2af0c80df8d7ed": {
689
+ "model_module": "@jupyter-widgets/controls",
690
+ "model_name": "DescriptionStyleModel",
691
+ "model_module_version": "1.5.0",
692
+ "state": {
693
+ "_model_module": "@jupyter-widgets/controls",
694
+ "_model_module_version": "1.5.0",
695
+ "_model_name": "DescriptionStyleModel",
696
+ "_view_count": null,
697
+ "_view_module": "@jupyter-widgets/base",
698
+ "_view_module_version": "1.2.0",
699
+ "_view_name": "StyleView",
700
+ "description_width": ""
701
+ }
702
+ },
703
+ "c1d0418037b64e6181fdac95b767c66c": {
704
+ "model_module": "@jupyter-widgets/controls",
705
+ "model_name": "HBoxModel",
706
+ "model_module_version": "1.5.0",
707
+ "state": {
708
+ "_dom_classes": [],
709
+ "_model_module": "@jupyter-widgets/controls",
710
+ "_model_module_version": "1.5.0",
711
+ "_model_name": "HBoxModel",
712
+ "_view_count": null,
713
+ "_view_module": "@jupyter-widgets/controls",
714
+ "_view_module_version": "1.5.0",
715
+ "_view_name": "HBoxView",
716
+ "box_style": "",
717
+ "children": [
718
+ "IPY_MODEL_dae0da1fe971454a86e68303438314c7",
719
+ "IPY_MODEL_f3721e13bcc74fd6a358a0321c5783d3",
720
+ "IPY_MODEL_a42422b18cf9456ab33a89f2e54e63b8"
721
+ ],
722
+ "layout": "IPY_MODEL_721cd9d8346c4f198adeaa2f507f53e7"
723
+ }
724
+ },
725
+ "dae0da1fe971454a86e68303438314c7": {
726
+ "model_module": "@jupyter-widgets/controls",
727
+ "model_name": "HTMLModel",
728
+ "model_module_version": "1.5.0",
729
+ "state": {
730
+ "_dom_classes": [],
731
+ "_model_module": "@jupyter-widgets/controls",
732
+ "_model_module_version": "1.5.0",
733
+ "_model_name": "HTMLModel",
734
+ "_view_count": null,
735
+ "_view_module": "@jupyter-widgets/controls",
736
+ "_view_module_version": "1.5.0",
737
+ "_view_name": "HTMLView",
738
+ "description": "",
739
+ "description_tooltip": null,
740
+ "layout": "IPY_MODEL_a1d9b8b653d040a68e81c04cacb47f7c",
741
+ "placeholder": "​",
742
+ "style": "IPY_MODEL_67b937ba6c1a48c4ac5e1c5c67b339d9",
743
+ "value": "Downloading (…)37e8b/vocabulary.txt: 100%"
744
+ }
745
+ },
746
+ "f3721e13bcc74fd6a358a0321c5783d3": {
747
+ "model_module": "@jupyter-widgets/controls",
748
+ "model_name": "FloatProgressModel",
749
+ "model_module_version": "1.5.0",
750
+ "state": {
751
+ "_dom_classes": [],
752
+ "_model_module": "@jupyter-widgets/controls",
753
+ "_model_module_version": "1.5.0",
754
+ "_model_name": "FloatProgressModel",
755
+ "_view_count": null,
756
+ "_view_module": "@jupyter-widgets/controls",
757
+ "_view_module_version": "1.5.0",
758
+ "_view_name": "ProgressView",
759
+ "bar_style": "success",
760
+ "description": "",
761
+ "description_tooltip": null,
762
+ "layout": "IPY_MODEL_5b975261024b4e558229c541b77ab268",
763
+ "max": 459861,
764
+ "min": 0,
765
+ "orientation": "horizontal",
766
+ "style": "IPY_MODEL_30674f2fe7684a8fb0db22f7d4494802",
767
+ "value": 459861
768
+ }
769
+ },
770
+ "a42422b18cf9456ab33a89f2e54e63b8": {
771
+ "model_module": "@jupyter-widgets/controls",
772
+ "model_name": "HTMLModel",
773
+ "model_module_version": "1.5.0",
774
+ "state": {
775
+ "_dom_classes": [],
776
+ "_model_module": "@jupyter-widgets/controls",
777
+ "_model_module_version": "1.5.0",
778
+ "_model_name": "HTMLModel",
779
+ "_view_count": null,
780
+ "_view_module": "@jupyter-widgets/controls",
781
+ "_view_module_version": "1.5.0",
782
+ "_view_name": "HTMLView",
783
+ "description": "",
784
+ "description_tooltip": null,
785
+ "layout": "IPY_MODEL_a8c5f2a5344d449995b085d54475557b",
786
+ "placeholder": "​",
787
+ "style": "IPY_MODEL_ae006482b2e34354a5550e5e8ac5cd9e",
788
+ "value": " 460k/460k [00:00<00:00, 2.73MB/s]"
789
+ }
790
+ },
791
+ "721cd9d8346c4f198adeaa2f507f53e7": {
792
+ "model_module": "@jupyter-widgets/base",
793
+ "model_name": "LayoutModel",
794
+ "model_module_version": "1.2.0",
795
+ "state": {
796
+ "_model_module": "@jupyter-widgets/base",
797
+ "_model_module_version": "1.2.0",
798
+ "_model_name": "LayoutModel",
799
+ "_view_count": null,
800
+ "_view_module": "@jupyter-widgets/base",
801
+ "_view_module_version": "1.2.0",
802
+ "_view_name": "LayoutView",
803
+ "align_content": null,
804
+ "align_items": null,
805
+ "align_self": null,
806
+ "border": null,
807
+ "bottom": null,
808
+ "display": null,
809
+ "flex": null,
810
+ "flex_flow": null,
811
+ "grid_area": null,
812
+ "grid_auto_columns": null,
813
+ "grid_auto_flow": null,
814
+ "grid_auto_rows": null,
815
+ "grid_column": null,
816
+ "grid_gap": null,
817
+ "grid_row": null,
818
+ "grid_template_areas": null,
819
+ "grid_template_columns": null,
820
+ "grid_template_rows": null,
821
+ "height": null,
822
+ "justify_content": null,
823
+ "justify_items": null,
824
+ "left": null,
825
+ "margin": null,
826
+ "max_height": null,
827
+ "max_width": null,
828
+ "min_height": null,
829
+ "min_width": null,
830
+ "object_fit": null,
831
+ "object_position": null,
832
+ "order": null,
833
+ "overflow": null,
834
+ "overflow_x": null,
835
+ "overflow_y": null,
836
+ "padding": null,
837
+ "right": null,
838
+ "top": null,
839
+ "visibility": null,
840
+ "width": null
841
+ }
842
+ },
843
+ "a1d9b8b653d040a68e81c04cacb47f7c": {
844
+ "model_module": "@jupyter-widgets/base",
845
+ "model_name": "LayoutModel",
846
+ "model_module_version": "1.2.0",
847
+ "state": {
848
+ "_model_module": "@jupyter-widgets/base",
849
+ "_model_module_version": "1.2.0",
850
+ "_model_name": "LayoutModel",
851
+ "_view_count": null,
852
+ "_view_module": "@jupyter-widgets/base",
853
+ "_view_module_version": "1.2.0",
854
+ "_view_name": "LayoutView",
855
+ "align_content": null,
856
+ "align_items": null,
857
+ "align_self": null,
858
+ "border": null,
859
+ "bottom": null,
860
+ "display": null,
861
+ "flex": null,
862
+ "flex_flow": null,
863
+ "grid_area": null,
864
+ "grid_auto_columns": null,
865
+ "grid_auto_flow": null,
866
+ "grid_auto_rows": null,
867
+ "grid_column": null,
868
+ "grid_gap": null,
869
+ "grid_row": null,
870
+ "grid_template_areas": null,
871
+ "grid_template_columns": null,
872
+ "grid_template_rows": null,
873
+ "height": null,
874
+ "justify_content": null,
875
+ "justify_items": null,
876
+ "left": null,
877
+ "margin": null,
878
+ "max_height": null,
879
+ "max_width": null,
880
+ "min_height": null,
881
+ "min_width": null,
882
+ "object_fit": null,
883
+ "object_position": null,
884
+ "order": null,
885
+ "overflow": null,
886
+ "overflow_x": null,
887
+ "overflow_y": null,
888
+ "padding": null,
889
+ "right": null,
890
+ "top": null,
891
+ "visibility": null,
892
+ "width": null
893
+ }
894
+ },
895
+ "67b937ba6c1a48c4ac5e1c5c67b339d9": {
896
+ "model_module": "@jupyter-widgets/controls",
897
+ "model_name": "DescriptionStyleModel",
898
+ "model_module_version": "1.5.0",
899
+ "state": {
900
+ "_model_module": "@jupyter-widgets/controls",
901
+ "_model_module_version": "1.5.0",
902
+ "_model_name": "DescriptionStyleModel",
903
+ "_view_count": null,
904
+ "_view_module": "@jupyter-widgets/base",
905
+ "_view_module_version": "1.2.0",
906
+ "_view_name": "StyleView",
907
+ "description_width": ""
908
+ }
909
+ },
910
+ "5b975261024b4e558229c541b77ab268": {
911
+ "model_module": "@jupyter-widgets/base",
912
+ "model_name": "LayoutModel",
913
+ "model_module_version": "1.2.0",
914
+ "state": {
915
+ "_model_module": "@jupyter-widgets/base",
916
+ "_model_module_version": "1.2.0",
917
+ "_model_name": "LayoutModel",
918
+ "_view_count": null,
919
+ "_view_module": "@jupyter-widgets/base",
920
+ "_view_module_version": "1.2.0",
921
+ "_view_name": "LayoutView",
922
+ "align_content": null,
923
+ "align_items": null,
924
+ "align_self": null,
925
+ "border": null,
926
+ "bottom": null,
927
+ "display": null,
928
+ "flex": null,
929
+ "flex_flow": null,
930
+ "grid_area": null,
931
+ "grid_auto_columns": null,
932
+ "grid_auto_flow": null,
933
+ "grid_auto_rows": null,
934
+ "grid_column": null,
935
+ "grid_gap": null,
936
+ "grid_row": null,
937
+ "grid_template_areas": null,
938
+ "grid_template_columns": null,
939
+ "grid_template_rows": null,
940
+ "height": null,
941
+ "justify_content": null,
942
+ "justify_items": null,
943
+ "left": null,
944
+ "margin": null,
945
+ "max_height": null,
946
+ "max_width": null,
947
+ "min_height": null,
948
+ "min_width": null,
949
+ "object_fit": null,
950
+ "object_position": null,
951
+ "order": null,
952
+ "overflow": null,
953
+ "overflow_x": null,
954
+ "overflow_y": null,
955
+ "padding": null,
956
+ "right": null,
957
+ "top": null,
958
+ "visibility": null,
959
+ "width": null
960
+ }
961
+ },
962
+ "30674f2fe7684a8fb0db22f7d4494802": {
963
+ "model_module": "@jupyter-widgets/controls",
964
+ "model_name": "ProgressStyleModel",
965
+ "model_module_version": "1.5.0",
966
+ "state": {
967
+ "_model_module": "@jupyter-widgets/controls",
968
+ "_model_module_version": "1.5.0",
969
+ "_model_name": "ProgressStyleModel",
970
+ "_view_count": null,
971
+ "_view_module": "@jupyter-widgets/base",
972
+ "_view_module_version": "1.2.0",
973
+ "_view_name": "StyleView",
974
+ "bar_color": null,
975
+ "description_width": ""
976
+ }
977
+ },
978
+ "a8c5f2a5344d449995b085d54475557b": {
979
+ "model_module": "@jupyter-widgets/base",
980
+ "model_name": "LayoutModel",
981
+ "model_module_version": "1.2.0",
982
+ "state": {
983
+ "_model_module": "@jupyter-widgets/base",
984
+ "_model_module_version": "1.2.0",
985
+ "_model_name": "LayoutModel",
986
+ "_view_count": null,
987
+ "_view_module": "@jupyter-widgets/base",
988
+ "_view_module_version": "1.2.0",
989
+ "_view_name": "LayoutView",
990
+ "align_content": null,
991
+ "align_items": null,
992
+ "align_self": null,
993
+ "border": null,
994
+ "bottom": null,
995
+ "display": null,
996
+ "flex": null,
997
+ "flex_flow": null,
998
+ "grid_area": null,
999
+ "grid_auto_columns": null,
1000
+ "grid_auto_flow": null,
1001
+ "grid_auto_rows": null,
1002
+ "grid_column": null,
1003
+ "grid_gap": null,
1004
+ "grid_row": null,
1005
+ "grid_template_areas": null,
1006
+ "grid_template_columns": null,
1007
+ "grid_template_rows": null,
1008
+ "height": null,
1009
+ "justify_content": null,
1010
+ "justify_items": null,
1011
+ "left": null,
1012
+ "margin": null,
1013
+ "max_height": null,
1014
+ "max_width": null,
1015
+ "min_height": null,
1016
+ "min_width": null,
1017
+ "object_fit": null,
1018
+ "object_position": null,
1019
+ "order": null,
1020
+ "overflow": null,
1021
+ "overflow_x": null,
1022
+ "overflow_y": null,
1023
+ "padding": null,
1024
+ "right": null,
1025
+ "top": null,
1026
+ "visibility": null,
1027
+ "width": null
1028
+ }
1029
+ },
1030
+ "ae006482b2e34354a5550e5e8ac5cd9e": {
1031
+ "model_module": "@jupyter-widgets/controls",
1032
+ "model_name": "DescriptionStyleModel",
1033
+ "model_module_version": "1.5.0",
1034
+ "state": {
1035
+ "_model_module": "@jupyter-widgets/controls",
1036
+ "_model_module_version": "1.5.0",
1037
+ "_model_name": "DescriptionStyleModel",
1038
+ "_view_count": null,
1039
+ "_view_module": "@jupyter-widgets/base",
1040
+ "_view_module_version": "1.2.0",
1041
+ "_view_name": "StyleView",
1042
+ "description_width": ""
1043
+ }
1044
+ },
1045
+ "6e9e495362954976b7feaaf189ae5515": {
1046
+ "model_module": "@jupyter-widgets/controls",
1047
+ "model_name": "HBoxModel",
1048
+ "model_module_version": "1.5.0",
1049
+ "state": {
1050
+ "_dom_classes": [],
1051
+ "_model_module": "@jupyter-widgets/controls",
1052
+ "_model_module_version": "1.5.0",
1053
+ "_model_name": "HBoxModel",
1054
+ "_view_count": null,
1055
+ "_view_module": "@jupyter-widgets/controls",
1056
+ "_view_module_version": "1.5.0",
1057
+ "_view_name": "HBoxView",
1058
+ "box_style": "",
1059
+ "children": [
1060
+ "IPY_MODEL_64d75dd1797c48df9dea1d3b2e67639a",
1061
+ "IPY_MODEL_7241c6f5e3204f98b61dd738e9e99138",
1062
+ "IPY_MODEL_c19d9f9d098a4cbe9774df0eaa4b93c6"
1063
+ ],
1064
+ "layout": "IPY_MODEL_530e0ab0e9a8416fa4a16fd80f638876"
1065
+ }
1066
+ },
1067
+ "64d75dd1797c48df9dea1d3b2e67639a": {
1068
+ "model_module": "@jupyter-widgets/controls",
1069
+ "model_name": "HTMLModel",
1070
+ "model_module_version": "1.5.0",
1071
+ "state": {
1072
+ "_dom_classes": [],
1073
+ "_model_module": "@jupyter-widgets/controls",
1074
+ "_model_module_version": "1.5.0",
1075
+ "_model_name": "HTMLModel",
1076
+ "_view_count": null,
1077
+ "_view_module": "@jupyter-widgets/controls",
1078
+ "_view_module_version": "1.5.0",
1079
+ "_view_name": "HTMLView",
1080
+ "description": "",
1081
+ "description_tooltip": null,
1082
+ "layout": "IPY_MODEL_b2f91e24777243caa58a5f7d3401cc3b",
1083
+ "placeholder": "​",
1084
+ "style": "IPY_MODEL_28002d9817f943719d4e405a87be21fb",
1085
+ "value": "Downloading model.bin: 100%"
1086
+ }
1087
+ },
1088
+ "7241c6f5e3204f98b61dd738e9e99138": {
1089
+ "model_module": "@jupyter-widgets/controls",
1090
+ "model_name": "FloatProgressModel",
1091
+ "model_module_version": "1.5.0",
1092
+ "state": {
1093
+ "_dom_classes": [],
1094
+ "_model_module": "@jupyter-widgets/controls",
1095
+ "_model_module_version": "1.5.0",
1096
+ "_model_name": "FloatProgressModel",
1097
+ "_view_count": null,
1098
+ "_view_module": "@jupyter-widgets/controls",
1099
+ "_view_module_version": "1.5.0",
1100
+ "_view_name": "ProgressView",
1101
+ "bar_style": "success",
1102
+ "description": "",
1103
+ "description_tooltip": null,
1104
+ "layout": "IPY_MODEL_ee8cf485818242a9b4c4fe8e3e80de84",
1105
+ "max": 3086912962,
1106
+ "min": 0,
1107
+ "orientation": "horizontal",
1108
+ "style": "IPY_MODEL_7d7aaff0c4bf4b01913454e660114731",
1109
+ "value": 3086912962
1110
+ }
1111
+ },
1112
+ "c19d9f9d098a4cbe9774df0eaa4b93c6": {
1113
+ "model_module": "@jupyter-widgets/controls",
1114
+ "model_name": "HTMLModel",
1115
+ "model_module_version": "1.5.0",
1116
+ "state": {
1117
+ "_dom_classes": [],
1118
+ "_model_module": "@jupyter-widgets/controls",
1119
+ "_model_module_version": "1.5.0",
1120
+ "_model_name": "HTMLModel",
1121
+ "_view_count": null,
1122
+ "_view_module": "@jupyter-widgets/controls",
1123
+ "_view_module_version": "1.5.0",
1124
+ "_view_name": "HTMLView",
1125
+ "description": "",
1126
+ "description_tooltip": null,
1127
+ "layout": "IPY_MODEL_85040b15c3324c7680a1fe93cf4c4dce",
1128
+ "placeholder": "​",
1129
+ "style": "IPY_MODEL_cafd4fecf63547e099e9b54f610252c6",
1130
+ "value": " 3.09G/3.09G [00:27<00:00, 58.7MB/s]"
1131
+ }
1132
+ },
1133
+ "530e0ab0e9a8416fa4a16fd80f638876": {
1134
+ "model_module": "@jupyter-widgets/base",
1135
+ "model_name": "LayoutModel",
1136
+ "model_module_version": "1.2.0",
1137
+ "state": {
1138
+ "_model_module": "@jupyter-widgets/base",
1139
+ "_model_module_version": "1.2.0",
1140
+ "_model_name": "LayoutModel",
1141
+ "_view_count": null,
1142
+ "_view_module": "@jupyter-widgets/base",
1143
+ "_view_module_version": "1.2.0",
1144
+ "_view_name": "LayoutView",
1145
+ "align_content": null,
1146
+ "align_items": null,
1147
+ "align_self": null,
1148
+ "border": null,
1149
+ "bottom": null,
1150
+ "display": null,
1151
+ "flex": null,
1152
+ "flex_flow": null,
1153
+ "grid_area": null,
1154
+ "grid_auto_columns": null,
1155
+ "grid_auto_flow": null,
1156
+ "grid_auto_rows": null,
1157
+ "grid_column": null,
1158
+ "grid_gap": null,
1159
+ "grid_row": null,
1160
+ "grid_template_areas": null,
1161
+ "grid_template_columns": null,
1162
+ "grid_template_rows": null,
1163
+ "height": null,
1164
+ "justify_content": null,
1165
+ "justify_items": null,
1166
+ "left": null,
1167
+ "margin": null,
1168
+ "max_height": null,
1169
+ "max_width": null,
1170
+ "min_height": null,
1171
+ "min_width": null,
1172
+ "object_fit": null,
1173
+ "object_position": null,
1174
+ "order": null,
1175
+ "overflow": null,
1176
+ "overflow_x": null,
1177
+ "overflow_y": null,
1178
+ "padding": null,
1179
+ "right": null,
1180
+ "top": null,
1181
+ "visibility": null,
1182
+ "width": null
1183
+ }
1184
+ },
1185
+ "b2f91e24777243caa58a5f7d3401cc3b": {
1186
+ "model_module": "@jupyter-widgets/base",
1187
+ "model_name": "LayoutModel",
1188
+ "model_module_version": "1.2.0",
1189
+ "state": {
1190
+ "_model_module": "@jupyter-widgets/base",
1191
+ "_model_module_version": "1.2.0",
1192
+ "_model_name": "LayoutModel",
1193
+ "_view_count": null,
1194
+ "_view_module": "@jupyter-widgets/base",
1195
+ "_view_module_version": "1.2.0",
1196
+ "_view_name": "LayoutView",
1197
+ "align_content": null,
1198
+ "align_items": null,
1199
+ "align_self": null,
1200
+ "border": null,
1201
+ "bottom": null,
1202
+ "display": null,
1203
+ "flex": null,
1204
+ "flex_flow": null,
1205
+ "grid_area": null,
1206
+ "grid_auto_columns": null,
1207
+ "grid_auto_flow": null,
1208
+ "grid_auto_rows": null,
1209
+ "grid_column": null,
1210
+ "grid_gap": null,
1211
+ "grid_row": null,
1212
+ "grid_template_areas": null,
1213
+ "grid_template_columns": null,
1214
+ "grid_template_rows": null,
1215
+ "height": null,
1216
+ "justify_content": null,
1217
+ "justify_items": null,
1218
+ "left": null,
1219
+ "margin": null,
1220
+ "max_height": null,
1221
+ "max_width": null,
1222
+ "min_height": null,
1223
+ "min_width": null,
1224
+ "object_fit": null,
1225
+ "object_position": null,
1226
+ "order": null,
1227
+ "overflow": null,
1228
+ "overflow_x": null,
1229
+ "overflow_y": null,
1230
+ "padding": null,
1231
+ "right": null,
1232
+ "top": null,
1233
+ "visibility": null,
1234
+ "width": null
1235
+ }
1236
+ },
1237
+ "28002d9817f943719d4e405a87be21fb": {
1238
+ "model_module": "@jupyter-widgets/controls",
1239
+ "model_name": "DescriptionStyleModel",
1240
+ "model_module_version": "1.5.0",
1241
+ "state": {
1242
+ "_model_module": "@jupyter-widgets/controls",
1243
+ "_model_module_version": "1.5.0",
1244
+ "_model_name": "DescriptionStyleModel",
1245
+ "_view_count": null,
1246
+ "_view_module": "@jupyter-widgets/base",
1247
+ "_view_module_version": "1.2.0",
1248
+ "_view_name": "StyleView",
1249
+ "description_width": ""
1250
+ }
1251
+ },
1252
+ "ee8cf485818242a9b4c4fe8e3e80de84": {
1253
+ "model_module": "@jupyter-widgets/base",
1254
+ "model_name": "LayoutModel",
1255
+ "model_module_version": "1.2.0",
1256
+ "state": {
1257
+ "_model_module": "@jupyter-widgets/base",
1258
+ "_model_module_version": "1.2.0",
1259
+ "_model_name": "LayoutModel",
1260
+ "_view_count": null,
1261
+ "_view_module": "@jupyter-widgets/base",
1262
+ "_view_module_version": "1.2.0",
1263
+ "_view_name": "LayoutView",
1264
+ "align_content": null,
1265
+ "align_items": null,
1266
+ "align_self": null,
1267
+ "border": null,
1268
+ "bottom": null,
1269
+ "display": null,
1270
+ "flex": null,
1271
+ "flex_flow": null,
1272
+ "grid_area": null,
1273
+ "grid_auto_columns": null,
1274
+ "grid_auto_flow": null,
1275
+ "grid_auto_rows": null,
1276
+ "grid_column": null,
1277
+ "grid_gap": null,
1278
+ "grid_row": null,
1279
+ "grid_template_areas": null,
1280
+ "grid_template_columns": null,
1281
+ "grid_template_rows": null,
1282
+ "height": null,
1283
+ "justify_content": null,
1284
+ "justify_items": null,
1285
+ "left": null,
1286
+ "margin": null,
1287
+ "max_height": null,
1288
+ "max_width": null,
1289
+ "min_height": null,
1290
+ "min_width": null,
1291
+ "object_fit": null,
1292
+ "object_position": null,
1293
+ "order": null,
1294
+ "overflow": null,
1295
+ "overflow_x": null,
1296
+ "overflow_y": null,
1297
+ "padding": null,
1298
+ "right": null,
1299
+ "top": null,
1300
+ "visibility": null,
1301
+ "width": null
1302
+ }
1303
+ },
1304
+ "7d7aaff0c4bf4b01913454e660114731": {
1305
+ "model_module": "@jupyter-widgets/controls",
1306
+ "model_name": "ProgressStyleModel",
1307
+ "model_module_version": "1.5.0",
1308
+ "state": {
1309
+ "_model_module": "@jupyter-widgets/controls",
1310
+ "_model_module_version": "1.5.0",
1311
+ "_model_name": "ProgressStyleModel",
1312
+ "_view_count": null,
1313
+ "_view_module": "@jupyter-widgets/base",
1314
+ "_view_module_version": "1.2.0",
1315
+ "_view_name": "StyleView",
1316
+ "bar_color": null,
1317
+ "description_width": ""
1318
+ }
1319
+ },
1320
+ "85040b15c3324c7680a1fe93cf4c4dce": {
1321
+ "model_module": "@jupyter-widgets/base",
1322
+ "model_name": "LayoutModel",
1323
+ "model_module_version": "1.2.0",
1324
+ "state": {
1325
+ "_model_module": "@jupyter-widgets/base",
1326
+ "_model_module_version": "1.2.0",
1327
+ "_model_name": "LayoutModel",
1328
+ "_view_count": null,
1329
+ "_view_module": "@jupyter-widgets/base",
1330
+ "_view_module_version": "1.2.0",
1331
+ "_view_name": "LayoutView",
1332
+ "align_content": null,
1333
+ "align_items": null,
1334
+ "align_self": null,
1335
+ "border": null,
1336
+ "bottom": null,
1337
+ "display": null,
1338
+ "flex": null,
1339
+ "flex_flow": null,
1340
+ "grid_area": null,
1341
+ "grid_auto_columns": null,
1342
+ "grid_auto_flow": null,
1343
+ "grid_auto_rows": null,
1344
+ "grid_column": null,
1345
+ "grid_gap": null,
1346
+ "grid_row": null,
1347
+ "grid_template_areas": null,
1348
+ "grid_template_columns": null,
1349
+ "grid_template_rows": null,
1350
+ "height": null,
1351
+ "justify_content": null,
1352
+ "justify_items": null,
1353
+ "left": null,
1354
+ "margin": null,
1355
+ "max_height": null,
1356
+ "max_width": null,
1357
+ "min_height": null,
1358
+ "min_width": null,
1359
+ "object_fit": null,
1360
+ "object_position": null,
1361
+ "order": null,
1362
+ "overflow": null,
1363
+ "overflow_x": null,
1364
+ "overflow_y": null,
1365
+ "padding": null,
1366
+ "right": null,
1367
+ "top": null,
1368
+ "visibility": null,
1369
+ "width": null
1370
+ }
1371
+ },
1372
+ "cafd4fecf63547e099e9b54f610252c6": {
1373
+ "model_module": "@jupyter-widgets/controls",
1374
+ "model_name": "DescriptionStyleModel",
1375
+ "model_module_version": "1.5.0",
1376
+ "state": {
1377
+ "_model_module": "@jupyter-widgets/controls",
1378
+ "_model_module_version": "1.5.0",
1379
+ "_model_name": "DescriptionStyleModel",
1380
+ "_view_count": null,
1381
+ "_view_module": "@jupyter-widgets/base",
1382
+ "_view_module_version": "1.2.0",
1383
+ "_view_name": "StyleView",
1384
+ "description_width": ""
1385
+ }
1386
+ }
1387
+ }
1388
+ }
1389
+ },
1390
+ "cells": [
1391
+ {
1392
+ "cell_type": "markdown",
1393
+ "source": [
1394
+ "# Audio (mp3) to Transcript"
1395
+ ],
1396
+ "metadata": {
1397
+ "id": "kNt1V_xZCYzb"
1398
+ }
1399
+ },
1400
+ {
1401
+ "cell_type": "markdown",
1402
+ "source": [
1403
+ "- Author: [Pierre Guillou](https://www.linkedin.com/in/pierreguillou/)\n",
1404
+ "- Date: 08/10/2023"
1405
+ ],
1406
+ "metadata": {
1407
+ "id": "Fa6V8oEynFe-"
1408
+ }
1409
+ },
1410
+ {
1411
+ "cell_type": "code",
1412
+ "source": [
1413
+ "%%capture\n",
1414
+ "!pip install -q faster-whisper\n",
1415
+ "!pip install gradio"
1416
+ ],
1417
+ "metadata": {
1418
+ "id": "S4yB5r9RCdkH"
1419
+ },
1420
+ "execution_count": 1,
1421
+ "outputs": []
1422
+ },
1423
+ {
1424
+ "cell_type": "code",
1425
+ "source": [
1426
+ "import gradio as gr\n",
1427
+ "import torch\n",
1428
+ "from faster_whisper import WhisperModel\n",
1429
+ "import pandas as pd\n",
1430
+ "\n",
1431
+ "model_size = \"large-v2\"\n",
1432
+ "\n",
1433
+ "# get device\n",
1434
+ "device = \"cuda:0\" if torch.cuda.is_available() else \"cpu\"\n",
1435
+ "\n",
1436
+ "if device == \"cuda:0\":\n",
1437
+ " # Run on GPU with FP16\n",
1438
+ " model_whisper = WhisperModel(model_size, device=\"cuda\", compute_type=\"float16\")\n",
1439
+ " # or Run on GPU with INT8\n",
1440
+ " # model = WhisperModel(model_size, device=\"cuda\", compute_type=\"int8_float16\")\n",
1441
+ "else:\n",
1442
+ " # Run on CPU with INT8\n",
1443
+ " model_whisper = WhisperModel(model_size, device=\"cpu\", compute_type=\"int8\")"
1444
+ ],
1445
+ "metadata": {
1446
+ "colab": {
1447
+ "base_uri": "https://localhost:8080/",
1448
+ "height": 145,
1449
+ "referenced_widgets": [
1450
+ "343b14a08a624631a28a08b7ada72068",
1451
+ "2f4ca8f678714e2e9e20ae2ca0b39504",
1452
+ "6afac288fbca4db7a37d7e18ea28240a",
1453
+ "c685a989f0e0488597ecc7bf51ca850b",
1454
+ "9d7c0834891940bbaf92011c504eb5ad",
1455
+ "2e53b75876134027a1b274684fa6cc24",
1456
+ "ccab9f55d52b4f608ffb0cd40176eb91",
1457
+ "48d7a28c4f01483a8bb46a381ae17e85",
1458
+ "1bab5f1a6be9419bab993bd05f72ac41",
1459
+ "747d4ae8cbcc44bdbcff49bde7d14aa6",
1460
+ "710b950a3e0449088a178950aad5a15e",
1461
+ "ad5dceffcb9f4525b8cb4fbbbfb67d03",
1462
+ "6c92704bacd2407382d3a00496297455",
1463
+ "0c466ba4c4334d759313e8be7546735a",
1464
+ "9c0f8ee844cb4ba4bd0b27bab5bc5907",
1465
+ "6a3dbb4e72ce41d691dcefc4c234ae54",
1466
+ "4d20f630401641f1b0bbf9aff2b8455b",
1467
+ "3ae150cecd064383bf1ae4da4d8ab510",
1468
+ "16e447b778734c6c8d75f2a571a2a146",
1469
+ "258e0ebf77fd4fd69feb43cca675b204",
1470
+ "2b7fbccaeec94dee85b4e943ebada9f6",
1471
+ "77ce76d5979d41478f2af0c80df8d7ed",
1472
+ "c1d0418037b64e6181fdac95b767c66c",
1473
+ "dae0da1fe971454a86e68303438314c7",
1474
+ "f3721e13bcc74fd6a358a0321c5783d3",
1475
+ "a42422b18cf9456ab33a89f2e54e63b8",
1476
+ "721cd9d8346c4f198adeaa2f507f53e7",
1477
+ "a1d9b8b653d040a68e81c04cacb47f7c",
1478
+ "67b937ba6c1a48c4ac5e1c5c67b339d9",
1479
+ "5b975261024b4e558229c541b77ab268",
1480
+ "30674f2fe7684a8fb0db22f7d4494802",
1481
+ "a8c5f2a5344d449995b085d54475557b",
1482
+ "ae006482b2e34354a5550e5e8ac5cd9e",
1483
+ "6e9e495362954976b7feaaf189ae5515",
1484
+ "64d75dd1797c48df9dea1d3b2e67639a",
1485
+ "7241c6f5e3204f98b61dd738e9e99138",
1486
+ "c19d9f9d098a4cbe9774df0eaa4b93c6",
1487
+ "530e0ab0e9a8416fa4a16fd80f638876",
1488
+ "b2f91e24777243caa58a5f7d3401cc3b",
1489
+ "28002d9817f943719d4e405a87be21fb",
1490
+ "ee8cf485818242a9b4c4fe8e3e80de84",
1491
+ "7d7aaff0c4bf4b01913454e660114731",
1492
+ "85040b15c3324c7680a1fe93cf4c4dce",
1493
+ "cafd4fecf63547e099e9b54f610252c6"
1494
+ ]
1495
+ },
1496
+ "id": "sdmZqI6N9v6s",
1497
+ "outputId": "b7cba541-8110-415d-e0a9-d3e131ac5076"
1498
+ },
1499
+ "execution_count": 2,
1500
+ "outputs": [
1501
+ {
1502
+ "output_type": "display_data",
1503
+ "data": {
1504
+ "text/plain": [
1505
+ "Downloading (…)37e8b/tokenizer.json: 0%| | 0.00/2.20M [00:00<?, ?B/s]"
1506
+ ],
1507
+ "application/vnd.jupyter.widget-view+json": {
1508
+ "version_major": 2,
1509
+ "version_minor": 0,
1510
+ "model_id": "343b14a08a624631a28a08b7ada72068"
1511
+ }
1512
+ },
1513
+ "metadata": {}
1514
+ },
1515
+ {
1516
+ "output_type": "display_data",
1517
+ "data": {
1518
+ "text/plain": [
1519
+ "Downloading (…)08837e8b/config.json: 0%| | 0.00/2.80k [00:00<?, ?B/s]"
1520
+ ],
1521
+ "application/vnd.jupyter.widget-view+json": {
1522
+ "version_major": 2,
1523
+ "version_minor": 0,
1524
+ "model_id": "ad5dceffcb9f4525b8cb4fbbbfb67d03"
1525
+ }
1526
+ },
1527
+ "metadata": {}
1528
+ },
1529
+ {
1530
+ "output_type": "display_data",
1531
+ "data": {
1532
+ "text/plain": [
1533
+ "Downloading (…)37e8b/vocabulary.txt: 0%| | 0.00/460k [00:00<?, ?B/s]"
1534
+ ],
1535
+ "application/vnd.jupyter.widget-view+json": {
1536
+ "version_major": 2,
1537
+ "version_minor": 0,
1538
+ "model_id": "c1d0418037b64e6181fdac95b767c66c"
1539
+ }
1540
+ },
1541
+ "metadata": {}
1542
+ },
1543
+ {
1544
+ "output_type": "display_data",
1545
+ "data": {
1546
+ "text/plain": [
1547
+ "Downloading model.bin: 0%| | 0.00/3.09G [00:00<?, ?B/s]"
1548
+ ],
1549
+ "application/vnd.jupyter.widget-view+json": {
1550
+ "version_major": 2,
1551
+ "version_minor": 0,
1552
+ "model_id": "6e9e495362954976b7feaaf189ae5515"
1553
+ }
1554
+ },
1555
+ "metadata": {}
1556
+ }
1557
+ ]
1558
+ },
1559
+ {
1560
+ "cell_type": "code",
1561
+ "source": [
1562
+ "def get_filename(file_obj):\n",
1563
+ " return file_obj.name.split(\"/\")[-1]\n",
1564
+ "\n",
1565
+ "def audio_to_transcript(file_obj):\n",
1566
+ " # get all audio segments\n",
1567
+ " try:\n",
1568
+ " filename = get_filename(file_obj)\n",
1569
+ " segments, _ = model_whisper.transcribe(file_obj.name, beam_size=5, vad_filter=True)\n",
1570
+ " except:\n",
1571
+ " filename = file_obj.split(\"/\")[-1]\n",
1572
+ " segments, _ = model_whisper.transcribe(file_obj, beam_size=5, vad_filter=True)\n",
1573
+ "\n",
1574
+ " start_segments, end_segments, text_segments = list(), list(), list()\n",
1575
+ " for segment in segments:\n",
1576
+ " start, end, text = segment.start, segment.end, segment.text\n",
1577
+ " start_segments.append(start)\n",
1578
+ " end_segments.append(end)\n",
1579
+ " text_segments.append(text)\n",
1580
+ "\n",
1581
+ " # save transcript into csv\n",
1582
+ " df = pd.DataFrame()\n",
1583
+ " df[\"start\"] = start_segments\n",
1584
+ " df[\"end\"] = end_segments\n",
1585
+ " df[\"text\"] = text_segments\n",
1586
+ "\n",
1587
+ " csv_file = filename.split(\".\")[0] + \".csv\"\n",
1588
+ " df.to_csv(csv_file, encoding=\"utf-8\", index=False)\n",
1589
+ " path_to_csv = gr.File.update(value=csv_file, visible=True)\n",
1590
+ "\n",
1591
+ " return filename, path_to_csv, df"
1592
+ ],
1593
+ "metadata": {
1594
+ "id": "vmxXLQRyJn00"
1595
+ },
1596
+ "execution_count": 12,
1597
+ "outputs": []
1598
+ },
1599
+ {
1600
+ "cell_type": "code",
1601
+ "source": [
1602
+ "## Gradio interface\n",
1603
+ "headers = [\"start\", \"end\", \"text\"]\n",
1604
+ "iface = gr.Interface(fn=audio_to_transcript,\n",
1605
+ " inputs=gr.File(label=\"Audio file\"),\n",
1606
+ " outputs=[\n",
1607
+ " gr.Textbox(label=\"Audio file name\"),\n",
1608
+ " gr.File(label=\"Transcript csv file\"),\n",
1609
+ " gr.DataFrame(label=\"Transcript\", headers=headers),\n",
1610
+ " ],\n",
1611
+ " allow_flagging=\"never\",\n",
1612
+ " title=\"Audio to Transcript\",\n",
1613
+ " description=\"Just paste any audio file and get its corresponding transcript with timeline.\",\n",
1614
+ " )\n",
1615
+ "iface.launch()"
1616
+ ],
1617
+ "metadata": {
1618
+ "id": "vYm0qelyU1F2"
1619
+ },
1620
+ "execution_count": null,
1621
+ "outputs": []
1622
+ },
1623
+ {
1624
+ "cell_type": "markdown",
1625
+ "source": [
1626
+ "# END"
1627
+ ],
1628
+ "metadata": {
1629
+ "id": "u9QYxqjtnzCD"
1630
+ }
1631
+ }
1632
+ ]
1633
+ }