jraramhoej
commited on
Commit
•
9612251
1
Parent(s):
dc4f202
update model card README.md
Browse files- README.md +78 -0
- fine-tune-whisper-streaming.ipynb +39 -20
README.md
ADDED
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- whisper-event
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- mozilla-foundation/common_voice_11_0
|
8 |
+
metrics:
|
9 |
+
- wer
|
10 |
+
model-index:
|
11 |
+
- name: Whisper Small Lithuanian and Serbian sequentially trained
|
12 |
+
results:
|
13 |
+
- task:
|
14 |
+
name: Automatic Speech Recognition
|
15 |
+
type: automatic-speech-recognition
|
16 |
+
dataset:
|
17 |
+
name: Common Voice 11.0
|
18 |
+
type: mozilla-foundation/common_voice_11_0
|
19 |
+
config: sr
|
20 |
+
split: test
|
21 |
+
args: sr
|
22 |
+
metrics:
|
23 |
+
- name: Wer
|
24 |
+
type: wer
|
25 |
+
value: 35.613112100364226
|
26 |
+
---
|
27 |
+
|
28 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
29 |
+
should probably proofread and complete it, then remove this comment. -->
|
30 |
+
|
31 |
+
# Whisper Small Lithuanian and Serbian sequentially trained
|
32 |
+
|
33 |
+
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 11.0 dataset.
|
34 |
+
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 0.6311
|
36 |
+
- Wer: 35.6131
|
37 |
+
|
38 |
+
## Model description
|
39 |
+
|
40 |
+
More information needed
|
41 |
+
|
42 |
+
## Intended uses & limitations
|
43 |
+
|
44 |
+
More information needed
|
45 |
+
|
46 |
+
## Training and evaluation data
|
47 |
+
|
48 |
+
More information needed
|
49 |
+
|
50 |
+
## Training procedure
|
51 |
+
|
52 |
+
### Training hyperparameters
|
53 |
+
|
54 |
+
The following hyperparameters were used during training:
|
55 |
+
- learning_rate: 1e-05
|
56 |
+
- train_batch_size: 64
|
57 |
+
- eval_batch_size: 8
|
58 |
+
- seed: 42
|
59 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
60 |
+
- lr_scheduler_type: linear
|
61 |
+
- lr_scheduler_warmup_steps: 500
|
62 |
+
- training_steps: 2000
|
63 |
+
- mixed_precision_training: Native AMP
|
64 |
+
|
65 |
+
### Training results
|
66 |
+
|
67 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
68 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
69 |
+
| 0.0003 | 49.01 | 1000 | 0.6035 | 26.7908 |
|
70 |
+
| 0.0002 | 99.01 | 2000 | 0.6311 | 35.6131 |
|
71 |
+
|
72 |
+
|
73 |
+
### Framework versions
|
74 |
+
|
75 |
+
- Transformers 4.26.0.dev0
|
76 |
+
- Pytorch 1.13.0+cu117
|
77 |
+
- Datasets 2.7.1.dev0
|
78 |
+
- Tokenizers 0.13.2
|
fine-tune-whisper-streaming.ipynb
CHANGED
@@ -1215,7 +1215,7 @@
|
|
1215 |
},
|
1216 |
{
|
1217 |
"cell_type": "code",
|
1218 |
-
"execution_count":
|
1219 |
"id": "95737cda-c5dd-4887-a4d0-dfcb0d61d977",
|
1220 |
"metadata": {},
|
1221 |
"outputs": [
|
@@ -1230,28 +1230,47 @@
|
|
1230 |
"tokenizer config file saved in ./tokenizer_config.json\n",
|
1231 |
"Special tokens file saved in ./special_tokens_map.json\n",
|
1232 |
"added tokens file saved in ./added_tokens.json\n",
|
1233 |
-
"Several commits (
|
1234 |
-
"The progress bars may be unreliable.\n"
|
1235 |
-
"fatal: unable to access 'https://huggingface.co/jraramhoej/whisper-small-lt-sr-v2/': The requested URL returned error: 502\n",
|
1236 |
-
"\n"
|
1237 |
]
|
1238 |
},
|
1239 |
{
|
1240 |
-
"
|
1241 |
-
|
1242 |
-
|
1243 |
-
|
1244 |
-
|
1245 |
-
|
1246 |
-
"
|
1247 |
-
|
1248 |
-
|
1249 |
-
|
1250 |
-
|
1251 |
-
|
1252 |
-
|
1253 |
-
|
1254 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1255 |
]
|
1256 |
}
|
1257 |
],
|
|
|
1215 |
},
|
1216 |
{
|
1217 |
"cell_type": "code",
|
1218 |
+
"execution_count": null,
|
1219 |
"id": "95737cda-c5dd-4887-a4d0-dfcb0d61d977",
|
1220 |
"metadata": {},
|
1221 |
"outputs": [
|
|
|
1230 |
"tokenizer config file saved in ./tokenizer_config.json\n",
|
1231 |
"Special tokens file saved in ./special_tokens_map.json\n",
|
1232 |
"added tokens file saved in ./added_tokens.json\n",
|
1233 |
+
"Several commits (3) will be pushed upstream.\n",
|
1234 |
+
"The progress bars may be unreliable.\n"
|
|
|
|
|
1235 |
]
|
1236 |
},
|
1237 |
{
|
1238 |
+
"data": {
|
1239 |
+
"application/vnd.jupyter.widget-view+json": {
|
1240 |
+
"model_id": "6b53c49cc54e4a3f88da039b5a18c439",
|
1241 |
+
"version_major": 2,
|
1242 |
+
"version_minor": 0
|
1243 |
+
},
|
1244 |
+
"text/plain": [
|
1245 |
+
"Upload file pytorch_model.bin: 0%| | 32.0k/922M [00:00<?, ?B/s]"
|
1246 |
+
]
|
1247 |
+
},
|
1248 |
+
"metadata": {},
|
1249 |
+
"output_type": "display_data"
|
1250 |
+
},
|
1251 |
+
{
|
1252 |
+
"data": {
|
1253 |
+
"application/vnd.jupyter.widget-view+json": {
|
1254 |
+
"model_id": "de9a0ebf1bf845229bdf5a78593d4852",
|
1255 |
+
"version_major": 2,
|
1256 |
+
"version_minor": 0
|
1257 |
+
},
|
1258 |
+
"text/plain": [
|
1259 |
+
"Upload file runs/Dec15_14-18-11_129-213-18-196/events.out.tfevents.1671113929.129-213-18-196.4128231.0: 100%|#…"
|
1260 |
+
]
|
1261 |
+
},
|
1262 |
+
"metadata": {},
|
1263 |
+
"output_type": "display_data"
|
1264 |
+
},
|
1265 |
+
{
|
1266 |
+
"name": "stderr",
|
1267 |
+
"output_type": "stream",
|
1268 |
+
"text": [
|
1269 |
+
"remote: Scanning LFS files for validity, may be slow... \n",
|
1270 |
+
"remote: LFS file scan complete. \n",
|
1271 |
+
"To https://huggingface.co/jraramhoej/whisper-small-lt-sr-v2\n",
|
1272 |
+
" 36a641a..dc4f202 main -> main\n",
|
1273 |
+
"\n"
|
1274 |
]
|
1275 |
}
|
1276 |
],
|