Update README.md

README.md

@@ -9,13 +9,26 @@ tags:
 ---
 # Matcha-TTS CommonVoice EN001 
 
-Audio
+## Source Audio
 https://commonvoice.mozilla.org/en/datasets
-I called Corps 1 of audios 42da7f26(head-audio-id)_290(files) EN001
+Common Voice Corpus 1
 
-Train with IPA(this folk)
+I called audios 42da7f26(head-audio-id)_290(files) EN001
+(No plan to include audios in this repo)
+## Any Good point?
+LJSpeech is much better quality,but it's female voice.
+
+VCTK 107 voices are similar quality,but that is ODC-By License.
+
+This audio is just under MIT more easy to continue training or something.
+## How to Train
+Train with IPA text(this folk)
 https://github.com/akjava/Matcha-TTS-Japanese
-## Files
+
+check this repo's config files.
+however there are no audio copy tools.TODO later
+
+## Files Info
 ### checkpoints
 Matcha-TTS checkpoint - epoch seems big but train with only 290 audios
 ### ONNX