Update README.md
Browse files
README.md
CHANGED
|
@@ -24,7 +24,7 @@ pipeline_tag: text-to-speech
|
|
| 24 |
**Main Idea:**
|
| 25 |
This model enhances previous Llasa TTS by incorporating multilingual data. The approach leverages the LLAMA-initialized text BPE tokenizer,
|
| 26 |
which is adept at handling multilingual text without the need to design language-specific G2P (grapheme-to-phoneme) systems.
|
| 27 |
-
Although the multilingual training data is limited—using only the MLS and Emilia datasets—resulting in potentially less optimal performance for some languages due to data scarcity,
|
| 28 |
our model can serve as a base TTS model. It is particularly suitable for fine-tuning for a specific language, as texts in various languages can be uniformly processed using the BPE tokenizer from Llama.
|
| 29 |
|
| 30 |
This model is not mentioned in the paper, but it follows the same methodology.
|
|
|
|
| 24 |
**Main Idea:**
|
| 25 |
This model enhances previous Llasa TTS by incorporating multilingual data. The approach leverages the LLAMA-initialized text BPE tokenizer,
|
| 26 |
which is adept at handling multilingual text without the need to design language-specific G2P (grapheme-to-phoneme) systems.
|
| 27 |
+
Although the multilingual training data is limited—using only the MLS (En/Fr/De/Nl/Es/It/Pt/Pl) and Emilia (En/Zh/De/Fr/Ja/Ko) datasets—resulting in potentially less optimal performance for some languages due to data scarcity,
|
| 28 |
our model can serve as a base TTS model. It is particularly suitable for fine-tuning for a specific language, as texts in various languages can be uniformly processed using the BPE tokenizer from Llama.
|
| 29 |
|
| 30 |
This model is not mentioned in the paper, but it follows the same methodology.
|