Update README.md
Browse files
README.md
CHANGED
|
@@ -32,9 +32,6 @@ Our model, Llasa, is a text-to-speech (TTS) system that extends the text-based L
|
|
| 32 |
|
| 33 |
The method is seamlessly compatible with the Llama framework, making training TTS similar as training LLM (convert audios into single-codebook tokens and simply view it as a special language). It opens the possiblity of existing method for compression, acceleration and finetuning for LLM to be applied.
|
| 34 |
|
| 35 |
-
**More brief information of XCodec and XCodec2** can be found from
|
| 36 |
-
https://huggingface.co/HKUSTAudio/Llasa-3B/discussions/11
|
| 37 |
-
|
| 38 |
|
| 39 |
|
| 40 |
## How to use
|
|
|
|
| 32 |
|
| 33 |
The method is seamlessly compatible with the Llama framework, making training TTS similar as training LLM (convert audios into single-codebook tokens and simply view it as a special language). It opens the possiblity of existing method for compression, acceleration and finetuning for LLM to be applied.
|
| 34 |
|
|
|
|
|
|
|
|
|
|
| 35 |
|
| 36 |
|
| 37 |
## How to use
|