Update README.md
Browse files
README.md
CHANGED
|
@@ -11,6 +11,7 @@ tags:
|
|
| 11 |
- chinese
|
| 12 |
- spark-tts
|
| 13 |
- genshin
|
|
|
|
| 14 |
---
|
| 15 |
# Spark TTS finetuned in genshin charactors voices.
|
| 16 |
## available charactors
|
|
@@ -41,6 +42,8 @@ print(f'save audio_tokenizer to {audio_tokenizer_path}')
|
|
| 41 |
# Inference usage
|
| 42 |
* see code in ('https://github.com/nonwesjoe/genshin-sparktts')
|
| 43 |
* audio ouputs examples: (https://github.com/nonwesjoe/genshin-sparktts/tree/main/examples)
|
|
|
|
|
|
|
| 44 |
# Acknowledgement
|
| 45 |
* [Spark-TTS](https://github.com/SparkAudio/Spark-TTS)
|
| 46 |
* [Genshin dataset](https://huggingface.co/datasets/simon3000/genshin-voice)
|
|
|
|
| 11 |
- chinese
|
| 12 |
- spark-tts
|
| 13 |
- genshin
|
| 14 |
+
- float16
|
| 15 |
---
|
| 16 |
# Spark TTS finetuned in genshin charactors voices.
|
| 17 |
## available charactors
|
|
|
|
| 42 |
# Inference usage
|
| 43 |
* see code in ('https://github.com/nonwesjoe/genshin-sparktts')
|
| 44 |
* audio ouputs examples: (https://github.com/nonwesjoe/genshin-sparktts/tree/main/examples)
|
| 45 |
+
# Detail
|
| 46 |
+
* this model is trianed on float32 but saved as float16 for less VRAM and Storage usage.
|
| 47 |
# Acknowledgement
|
| 48 |
* [Spark-TTS](https://github.com/SparkAudio/Spark-TTS)
|
| 49 |
* [Genshin dataset](https://huggingface.co/datasets/simon3000/genshin-voice)
|