Commit
·
441fa65
1
Parent(s):
751d494
update README
Browse files- README.md +5 -8
- fine-tune-whisper-non-streaming.ipynb +68 -2
README.md
CHANGED
|
@@ -4,32 +4,29 @@ language:
|
|
| 4 |
license: apache-2.0
|
| 5 |
tags:
|
| 6 |
- whisper-event
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
datasets:
|
| 9 |
- mozilla-foundation/common_voice_11_0
|
| 10 |
metrics:
|
| 11 |
- wer
|
| 12 |
model-index:
|
| 13 |
-
- name:
|
| 14 |
results:
|
| 15 |
- task:
|
| 16 |
name: Automatic Speech Recognition
|
| 17 |
type: automatic-speech-recognition
|
| 18 |
dataset:
|
| 19 |
-
name:
|
| 20 |
type: mozilla-foundation/common_voice_11_0
|
| 21 |
-
config: ta
|
| 22 |
-
split:
|
| 23 |
-
args: ta
|
| 24 |
metrics:
|
| 25 |
- name: Wer
|
| 26 |
type: wer
|
| 27 |
value: 69.31938022227631
|
| 28 |
---
|
| 29 |
|
| 30 |
-
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 31 |
-
should probably proofread and complete it, then remove this comment. -->
|
| 32 |
-
|
| 33 |
#
|
| 34 |
|
| 35 |
This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the Common Voice 11.0 dataset.
|
|
|
|
| 4 |
license: apache-2.0
|
| 5 |
tags:
|
| 6 |
- whisper-event
|
| 7 |
+
- hf-asr-leaderboard
|
| 8 |
- generated_from_trainer
|
| 9 |
datasets:
|
| 10 |
- mozilla-foundation/common_voice_11_0
|
| 11 |
metrics:
|
| 12 |
- wer
|
| 13 |
model-index:
|
| 14 |
+
- name: whisper_tamil_medium
|
| 15 |
results:
|
| 16 |
- task:
|
| 17 |
name: Automatic Speech Recognition
|
| 18 |
type: automatic-speech-recognition
|
| 19 |
dataset:
|
| 20 |
+
name: mozilla-foundation/common_voice_11_0
|
| 21 |
type: mozilla-foundation/common_voice_11_0
|
| 22 |
+
config: ta
|
| 23 |
+
split: test
|
|
|
|
| 24 |
metrics:
|
| 25 |
- name: Wer
|
| 26 |
type: wer
|
| 27 |
value: 69.31938022227631
|
| 28 |
---
|
| 29 |
|
|
|
|
|
|
|
|
|
|
| 30 |
#
|
| 31 |
|
| 32 |
This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the Common Voice 11.0 dataset.
|
fine-tune-whisper-non-streaming.ipynb
CHANGED
|
@@ -1421,7 +1421,7 @@
|
|
| 1421 |
},
|
| 1422 |
{
|
| 1423 |
"cell_type": "code",
|
| 1424 |
-
"execution_count":
|
| 1425 |
"id": "d7030622-caf7-4039-939b-6195cdaa2585",
|
| 1426 |
"metadata": {
|
| 1427 |
"id": "d7030622-caf7-4039-939b-6195cdaa2585"
|
|
@@ -1434,7 +1434,73 @@
|
|
| 1434 |
"Saving model checkpoint to ./\n",
|
| 1435 |
"Configuration saved in ./config.json\n",
|
| 1436 |
"Model weights saved in ./pytorch_model.bin\n",
|
| 1437 |
-
"Feature extractor saved in ./preprocessor_config.json\n"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1438 |
]
|
| 1439 |
}
|
| 1440 |
],
|
|
|
|
| 1421 |
},
|
| 1422 |
{
|
| 1423 |
"cell_type": "code",
|
| 1424 |
+
"execution_count": 31,
|
| 1425 |
"id": "d7030622-caf7-4039-939b-6195cdaa2585",
|
| 1426 |
"metadata": {
|
| 1427 |
"id": "d7030622-caf7-4039-939b-6195cdaa2585"
|
|
|
|
| 1434 |
"Saving model checkpoint to ./\n",
|
| 1435 |
"Configuration saved in ./config.json\n",
|
| 1436 |
"Model weights saved in ./pytorch_model.bin\n",
|
| 1437 |
+
"Feature extractor saved in ./preprocessor_config.json\n",
|
| 1438 |
+
"Several commits (3) will be pushed upstream.\n",
|
| 1439 |
+
"The progress bars may be unreliable.\n"
|
| 1440 |
+
]
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"data": {
|
| 1444 |
+
"application/json": {
|
| 1445 |
+
"ascii": false,
|
| 1446 |
+
"bar_format": null,
|
| 1447 |
+
"colour": null,
|
| 1448 |
+
"elapsed": 0.03398323059082031,
|
| 1449 |
+
"initial": 32768,
|
| 1450 |
+
"n": 32768,
|
| 1451 |
+
"ncols": null,
|
| 1452 |
+
"nrows": null,
|
| 1453 |
+
"postfix": null,
|
| 1454 |
+
"prefix": "Upload file pytorch_model.bin",
|
| 1455 |
+
"rate": null,
|
| 1456 |
+
"total": 3055754841,
|
| 1457 |
+
"unit": "B",
|
| 1458 |
+
"unit_divisor": 1024,
|
| 1459 |
+
"unit_scale": true
|
| 1460 |
+
},
|
| 1461 |
+
"application/vnd.jupyter.widget-view+json": {
|
| 1462 |
+
"model_id": "2dfe3607383d42a1aca683b577e8f052",
|
| 1463 |
+
"version_major": 2,
|
| 1464 |
+
"version_minor": 0
|
| 1465 |
+
},
|
| 1466 |
+
"text/plain": [
|
| 1467 |
+
"Upload file pytorch_model.bin: 0%| | 32.0k/2.85G [00:00<?, ?B/s]"
|
| 1468 |
+
]
|
| 1469 |
+
},
|
| 1470 |
+
"metadata": {},
|
| 1471 |
+
"output_type": "display_data"
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"name": "stderr",
|
| 1475 |
+
"output_type": "stream",
|
| 1476 |
+
"text": [
|
| 1477 |
+
"remote: Scanning LFS files for validity, may be slow... \n",
|
| 1478 |
+
"remote: LFS file scan complete. \n",
|
| 1479 |
+
"remote: ----------------------------------------------------------\u001b[0;31m \n",
|
| 1480 |
+
"remote: Sorry, your push was rejected during YAML metadata verification: \n",
|
| 1481 |
+
"remote: - Error: \"model-index[0].name\" is not allowed to be empty\u001b[0;32m \n",
|
| 1482 |
+
"remote: ---------------------------------------------------------- \n",
|
| 1483 |
+
"remote: Please find the documentation at: \n",
|
| 1484 |
+
"remote: https://huggingface.co/docs/hub/model-cards#model-card-metadata\u001b[0;0m \n",
|
| 1485 |
+
"remote: ---------------------------------------------------------- \n",
|
| 1486 |
+
"To https://huggingface.co/kurianbenoy/whisper-medium-tamil\n",
|
| 1487 |
+
" ! [remote rejected] main -> main (pre-receive hook declined)\n",
|
| 1488 |
+
"error: failed to push some refs to 'https://huggingface.co/kurianbenoy/whisper-medium-tamil'\n",
|
| 1489 |
+
"\n",
|
| 1490 |
+
"Error pushing update to the model card. Please read logs and retry.\n",
|
| 1491 |
+
"$remote: Scanning LFS files for validity, may be slow... \n",
|
| 1492 |
+
"remote: LFS file scan complete. \n",
|
| 1493 |
+
"remote: ----------------------------------------------------------\u001b[0;31m \n",
|
| 1494 |
+
"remote: Sorry, your push was rejected during YAML metadata verification: \n",
|
| 1495 |
+
"remote: - Error: \"model-index[0].name\" is not allowed to be empty\u001b[0;32m \n",
|
| 1496 |
+
"remote: ---------------------------------------------------------- \n",
|
| 1497 |
+
"remote: Please find the documentation at: \n",
|
| 1498 |
+
"remote: https://huggingface.co/docs/hub/model-cards#model-card-metadata\u001b[0;0m \n",
|
| 1499 |
+
"remote: ---------------------------------------------------------- \n",
|
| 1500 |
+
"To https://huggingface.co/kurianbenoy/whisper-medium-tamil\n",
|
| 1501 |
+
" ! [remote rejected] main -> main (pre-receive hook declined)\n",
|
| 1502 |
+
"error: failed to push some refs to 'https://huggingface.co/kurianbenoy/whisper-medium-tamil'\n",
|
| 1503 |
+
"\n"
|
| 1504 |
]
|
| 1505 |
}
|
| 1506 |
],
|