Update README.md
Browse filesAdded more details on the specific checkpoint being saved to huggingface
README.md
CHANGED
|
@@ -35,7 +35,28 @@ More information needed
|
|
| 35 |
|
| 36 |
## Training and evaluation data
|
| 37 |
|
| 38 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 39 |
|
| 40 |
## Training procedure
|
| 41 |
|
|
|
|
| 35 |
|
| 36 |
## Training and evaluation data
|
| 37 |
|
| 38 |
+
Step Training Loss Validation Loss Wer
|
| 39 |
+
40 9.648200 4.719201 1.000000
|
| 40 |
+
80 3.953400 3.477898 1.000000
|
| 41 |
+
120 3.289700 3.099611 1.000000
|
| 42 |
+
160 3.038400 2.993551 1.000000
|
| 43 |
+
200 2.994500 2.979574 1.000000
|
| 44 |
+
240 2.959000 2.941970 1.000000
|
| 45 |
+
280 2.802100 2.520133 1.000000
|
| 46 |
+
320 1.862100 1.499739 0.746423
|
| 47 |
+
360 1.191800 1.336315 0.610261
|
| 48 |
+
400 0.951300 1.317062 0.598915
|
| 49 |
+
440 0.773900 1.312918 0.614702
|
| 50 |
+
480 0.624700 1.376327 0.557967
|
| 51 |
+
|
| 52 |
+
/usr/local/lib/python3.10/dist-packages/transformers/models/wav2vec2/processing_wav2vec2.py:156: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.
|
| 53 |
+
warnings.warn(
|
| 54 |
+
/usr/local/lib/python3.10/dist-packages/torch/utils/checkpoint.py:460: UserWarning: torch.utils.checkpoint: please pass in use_reentrant=True or use_reentrant=False explicitly. The default value of use_reentrant will be updated to be False in the future. To maintain current behavior, pass use_reentrant=True. It is recommended that you use use_reentrant=False. Refer to docs for more details on the differences between the two variants.
|
| 55 |
+
warnings.warn(
|
| 56 |
+
/usr/local/lib/python3.10/dist-packages/transformers/models/wav2vec2/processing_wav2vec2.py:156: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.
|
| 57 |
+
warnings.warn(
|
| 58 |
+
/usr/local/lib/python3.10/dist-packages/torch/utils/checkpoint.py:460: UserWarning: torch.utils.checkpoint: please pass in use_reentrant=True or use_reentrant=False explicitly. The default value of use_reentrant will be updated to be False in the future. To maintain current behavior, pass use_reentrant=True. It is recommended that you use use_reentrant=False. Refer to docs for more details on the differences between the two variants.
|
| 59 |
+
warnings.warn(
|
| 60 |
|
| 61 |
## Training procedure
|
| 62 |
|