Commit
•
3dd3a85
1
Parent(s):
199e6d1
Update README.md
Browse files
README.md
CHANGED
|
@@ -3,4 +3,26 @@ license: mit
|
|
| 3 |
language:
|
| 4 |
- hak
|
| 5 |
pipeline_tag: text-to-speech
|
| 6 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
language:
|
| 4 |
- hak
|
| 5 |
pipeline_tag: text-to-speech
|
| 6 |
+
---
|
| 7 |
+
|
| 8 |
+
# Model Card for taiwanese-hakka-tts-sixian-hailu-mix
|
| 9 |
+
|
| 10 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 11 |
+
|
| 12 |
+
A experimental model to try speaker encoder.
|
| 13 |
+
|
| 14 |
+
## Model Details
|
| 15 |
+
|
| 16 |
+
- YourTTS
|
| 17 |
+
- sample rate: 16k
|
| 18 |
+
- Training data contain four persons
|
| 19 |
+
- Use speaker encoder output as speaker embedding
|
| 20 |
+
- Use language embedding
|
| 21 |
+
|
| 22 |
+
### Model Sources
|
| 23 |
+
|
| 24 |
+
<!-- Provide the basic links for the model. -->
|
| 25 |
+
|
| 26 |
+
- **Repository:** [coqui-ai/TTS](https://github.com/coqui-ai/TTS)
|
| 27 |
+
- **Demo:** [Hugging Face Space](https://huggingface.co/spaces/formospeech/taiwanese-hakka-tts)
|
| 28 |
+
|