Update README.md
Browse files
README.md
CHANGED
|
@@ -6,7 +6,7 @@ tags:
|
|
| 6 |
- speech
|
| 7 |
---
|
| 8 |
|
| 9 |
-
# WavLM-Base
|
| 10 |
|
| 11 |
[Microsoft's WavLM](https://github.com/microsoft/unilm/tree/master/wavlm)
|
| 12 |
|
|
@@ -23,6 +23,9 @@ Authors: Sanyuan Chen, Chengyi Wang, Zhengyang Chen, Yu Wu, Shujie Liu, Zhuo Che
|
|
| 23 |
|
| 24 |
The original model can be found under https://github.com/microsoft/unilm/tree/master/wavlm.
|
| 25 |
|
|
|
|
|
|
|
|
|
|
| 26 |
# Usage
|
| 27 |
## Speaker Diarization
|
| 28 |
```python
|
|
|
|
| 6 |
- speech
|
| 7 |
---
|
| 8 |
|
| 9 |
+
# WavLM-Base for Speaker Diarization
|
| 10 |
|
| 11 |
[Microsoft's WavLM](https://github.com/microsoft/unilm/tree/master/wavlm)
|
| 12 |
|
|
|
|
| 23 |
|
| 24 |
The original model can be found under https://github.com/microsoft/unilm/tree/master/wavlm.
|
| 25 |
|
| 26 |
+
# Fine-tuning details
|
| 27 |
+
The model is fine-tuned on the [LibriMix dataset](https://github.com/JorisCos/LibriMix) using just a linear layer for mapping the network outputs.
|
| 28 |
+
|
| 29 |
# Usage
|
| 30 |
## Speaker Diarization
|
| 31 |
```python
|