wannaphong commited on
Commit
ab4c571
1 Parent(s): 510b23c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -5
README.md CHANGED
@@ -4,9 +4,9 @@ license: apache-2.0
4
 
5
  # KhanomTan TTS v1.0
6
 
7
- KhnomTan TTS (ขนมตาล) is a open-source Thai text-to-speech model that supports multilingual speakers. It supports Thai, English, and others.
8
 
9
- KhnomTan TTS is a YourTTS model that trained with supports Thai. We add the Thai speech corpus from TSync 1* and TSync 2* to [mbarnig/lb-de-fr-en-pt-12800-TTS-CORPUS](https://huggingface.co/datasets/mbarnig/lb-de-fr-en-pt-12800-TTS-CORPUS) that train the model with YourTTS model.
10
 
11
  ## Config
12
  We have Thai characters to the graphemes config for training the model and use the Speaker Encoder model from the speaker encoder model from [🐸 Coqui-TTS](https://github.com/coqui-ai/TTS/releases/tag/speaker_encoder_model).
@@ -17,8 +17,8 @@ We add Tsync 1 corpus and Tsync 2 corpus, which are not complete datasets, and t
17
  ## Trained the model
18
  We use the 🐸 Coqui-TTS multilingual VITS-model recipe (version 0.7.1 or the commit id is d46fbc240ccf21797d42ac26cb27eb0b9f8d31c4) for training the model, and we use the speaker encoder model from [🐸 Coqui-TTS](https://github.com/coqui-ai/TTS/releases/tag/speaker_encoder_model) then we release the best model to public access.
19
 
20
- Model cards: ____
21
- Dataset (Tsync 1 and Tsync 2 only): ____
22
- GitHub: ____
23
 
24
  *Note: Those are not complete corpus. We can access the public corpus only.
4
 
5
  # KhanomTan TTS v1.0
6
 
7
+ KhanomTan TTS (ขนมตาล) is a open-source Thai text-to-speech model that supports multilingual speakers. It supports Thai, English, and others.
8
 
9
+ KhanomTan TTS is a YourTTS model that trained with supports Thai. We add the Thai speech corpus from TSync 1* and TSync 2* to [mbarnig/lb-de-fr-en-pt-12800-TTS-CORPUS](https://huggingface.co/datasets/mbarnig/lb-de-fr-en-pt-12800-TTS-CORPUS) that train the model with YourTTS model.
10
 
11
  ## Config
12
  We have Thai characters to the graphemes config for training the model and use the Speaker Encoder model from the speaker encoder model from [🐸 Coqui-TTS](https://github.com/coqui-ai/TTS/releases/tag/speaker_encoder_model).
17
  ## Trained the model
18
  We use the 🐸 Coqui-TTS multilingual VITS-model recipe (version 0.7.1 or the commit id is d46fbc240ccf21797d42ac26cb27eb0b9f8d31c4) for training the model, and we use the speaker encoder model from [🐸 Coqui-TTS](https://github.com/coqui-ai/TTS/releases/tag/speaker_encoder_model) then we release the best model to public access.
19
 
20
+ - Model cards: [https://github.com/wannaphong/KhanomTan-TTS-v1.0](https://github.com/wannaphong/KhanomTan-TTS-v1.0)
21
+ - Dataset (Tsync 1 and Tsync 2 only): [https://huggingface.co/datasets/wannaphong/tsync1-2-yourtts](https://huggingface.co/datasets/wannaphong/tsync1-2-yourtts)
22
+ - GitHub: [https://github.com/wannaphong/KhanomTan-TTS-v1.0](https://github.com/wannaphong/KhanomTan-TTS-v1.0)
23
 
24
  *Note: Those are not complete corpus. We can access the public corpus only.