indiejoseph
commited on
Update README.md
Browse files
README.md
CHANGED
@@ -1,7 +1,12 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
4 |
|
5 |
# cantonese-hubert-base-l9-k200
|
6 |
|
7 |
-
This is a fine-tuned Hubert model based on [TencentGameMate/chinese-hubert-base](https://huggingface.co/TencentGameMate/chinese-hubert-base) for generate speech discete units, The K-means model is trained on 9k+ hours Cantonese speech data, with 200 clusters and representations from 9th layer of the model.
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
datasets:
|
4 |
+
- alvanlii/cantonese-youtube
|
5 |
+
base_model:
|
6 |
+
- TencentGameMate/chinese-hubert-base
|
7 |
+
library_name: fairseq
|
8 |
---
|
9 |
|
10 |
# cantonese-hubert-base-l9-k200
|
11 |
|
12 |
+
This is a fine-tuned Hubert model based on [TencentGameMate/chinese-hubert-base](https://huggingface.co/TencentGameMate/chinese-hubert-base) for generate speech discete units, The K-means model is trained on [9k+ hours Cantonese speech data](https://huggingface.co/datasets/alvanlii/cantonese-youtube), with 200 clusters and representations from 9th layer of the model.
|