Hugging Face's logo

Akjava
/
matcha_tts_common_voice_01_en_001

Text-to-Speech
TensorBoard
ONNX
English
audio
matcha-tts
Model card Files Metrics Community
Akjava commited on
Commit
f0eab92
·
verified ·
1 Parent(s): e35d6d2

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -8,7 +8,7 @@ tags:
8
  - matcha-tts
9
  ---
10
  # Matcha-TTS CommonVoice EN001
11
- [Github Demo](https://akjava.github.io/Matcha-TTS-Japanese/matcha_tts_speak_en001.html)
12
 
13
  ## Source Audio
14
  https://commonvoice.mozilla.org/en/datasets
@@ -19,7 +19,7 @@ I called audios 42da7f26(head-audio-id)_290(files) EN001
19
  ## Any Good point?
20
  LJSpeech is much better quality,but it's female voice.This one is men.
21
 
22
- VCTK 107 voices are similar quality,but that is ODC-By License.
23
 
24
  This audio is just under MIT more easy to continue training or something.
25
 
 
8
  - matcha-tts
9
  ---
10
  # Matcha-TTS CommonVoice EN001
11
+ [you can test variation models](https://huggingface.co/spaces/Akjava/matcha-tts-onnx-benchmarks) | [Github Demo](https://akjava.github.io/Matcha-TTS-Japanese/matcha_tts_speak_en001.html)
12
 
13
  ## Source Audio
14
  https://commonvoice.mozilla.org/en/datasets
 
19
  ## Any Good point?
20
  LJSpeech is much better quality,but it's female voice.This one is men.
21
 
22
+ VCTK 109 voices are similar quality,but that is ODC-By License.
23
 
24
  This audio is just under MIT more easy to continue training or something.
25