Update README.md
Browse files
README.md
CHANGED
|
@@ -8,7 +8,10 @@ license: apache-2.0
|
|
| 8 |
---
|
| 9 |
|
| 10 |
# Wav2Vec2-Large-LV60
|
| 11 |
-
|
|
|
|
|
|
|
|
|
|
| 12 |
[Facebook's Wav2Vec2](https://ai.facebook.com/blog/wav2vec-20-learning-the-structure-of-speech-from-raw-audio/)
|
| 13 |
|
| 14 |
The base model pretrained on 16kHz sampled speech audio. When using the model make sure that your speech input is also sampled at 16Khz.
|
|
|
|
| 8 |
---
|
| 9 |
|
| 10 |
# Wav2Vec2-Large-LV60
|
| 11 |
+
Parameter changed:
|
| 12 |
+
"mask_time_prob": 0.05 changed to "mask_time_prob": 0.5.
|
| 13 |
+
Based on this link:https://github.com/huggingface/transformers/issues/16962 to make pre-training this model work.
|
| 14 |
+
|
| 15 |
[Facebook's Wav2Vec2](https://ai.facebook.com/blog/wav2vec-20-learning-the-structure-of-speech-from-raw-audio/)
|
| 16 |
|
| 17 |
The base model pretrained on 16kHz sampled speech audio. When using the model make sure that your speech input is also sampled at 16Khz.
|