EdoAbati commited on
Commit
b09898f
1 Parent(s): 7260b71

update model card README.md

Browse files
Files changed (2) hide show
  1. README.md +62 -0
  2. fine-tune-whisper-streaming.ipynb +41 -0
README.md ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - it
4
+ license: apache-2.0
5
+ tags:
6
+ - whisper-event
7
+ - generated_from_trainer
8
+ datasets:
9
+ - mozilla-foundation/common_voice_11_0
10
+ model-index:
11
+ - name: Whisper Small It - Edoardo Abati
12
+ results: []
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+ # Whisper Small It - Edoardo Abati
19
+
20
+ This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 11.0 dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - eval_loss: 0.2111
23
+ - eval_wer: 10.1352
24
+ - eval_runtime: 4736.3912
25
+ - eval_samples_per_second: 3.168
26
+ - eval_steps_per_second: 0.396
27
+ - epoch: 0.4
28
+ - step: 2000
29
+
30
+ ## Model description
31
+
32
+ More information needed
33
+
34
+ ## Intended uses & limitations
35
+
36
+ More information needed
37
+
38
+ ## Training and evaluation data
39
+
40
+ More information needed
41
+
42
+ ## Training procedure
43
+
44
+ ### Training hyperparameters
45
+
46
+ The following hyperparameters were used during training:
47
+ - learning_rate: 1e-05
48
+ - train_batch_size: 64
49
+ - eval_batch_size: 8
50
+ - seed: 42
51
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
+ - lr_scheduler_type: linear
53
+ - lr_scheduler_warmup_steps: 500
54
+ - training_steps: 5000
55
+ - mixed_precision_training: Native AMP
56
+
57
+ ### Framework versions
58
+
59
+ - Transformers 4.26.0.dev0
60
+ - Pytorch 1.13.0+cu117
61
+ - Datasets 2.7.1.dev0
62
+ - Tokenizers 0.13.2
fine-tune-whisper-streaming.ipynb CHANGED
@@ -1238,6 +1238,47 @@
1238
  "Special tokens file saved in ./special_tokens_map.json\n",
1239
  "added tokens file saved in ./added_tokens.json\n"
1240
  ]
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1241
  }
1242
  ],
1243
  "source": [
 
1238
  "Special tokens file saved in ./special_tokens_map.json\n",
1239
  "added tokens file saved in ./added_tokens.json\n"
1240
  ]
1241
+ },
1242
+ {
1243
+ "data": {
1244
+ "application/vnd.jupyter.widget-view+json": {
1245
+ "model_id": "308a037772114b6e97be821a2d5fa82d",
1246
+ "version_major": 2,
1247
+ "version_minor": 0
1248
+ },
1249
+ "text/plain": [
1250
+ "Upload file pytorch_model.bin: 0%| | 32.0k/922M [00:00<?, ?B/s]"
1251
+ ]
1252
+ },
1253
+ "metadata": {},
1254
+ "output_type": "display_data"
1255
+ },
1256
+ {
1257
+ "data": {
1258
+ "application/vnd.jupyter.widget-view+json": {
1259
+ "model_id": "019fd540558a4155bfc07de088d15d17",
1260
+ "version_major": 2,
1261
+ "version_minor": 0
1262
+ },
1263
+ "text/plain": [
1264
+ "Upload file runs/Dec07_20-55-49_155-248-246-251/events.out.tfevents.1670446586.155-248-246-251.72616.0: 100%|#…"
1265
+ ]
1266
+ },
1267
+ "metadata": {},
1268
+ "output_type": "display_data"
1269
+ },
1270
+ {
1271
+ "name": "stderr",
1272
+ "output_type": "stream",
1273
+ "text": [
1274
+ "remote: Scanning LFS files for validity, may be slow... \n",
1275
+ "remote: LFS file scan complete. \n",
1276
+ "To https://huggingface.co/EdoAbati/whisper-small-it\n",
1277
+ " 9255450..7260b71 main -> main\n",
1278
+ "\n",
1279
+ "Dropping the following result as it does not have all the necessary fields:\n",
1280
+ "{'task': {'name': 'Automatic Speech Recognition', 'type': 'automatic-speech-recognition'}, 'dataset': {'name': 'Common Voice 11.0', 'type': 'mozilla-foundation/common_voice_11_0', 'config': 'it', 'split': 'test', 'args': 'it'}}\n"
1281
+ ]
1282
  }
1283
  ],
1284
  "source": [