Akjava
/

matcha-tts_ja_single-speaker_merged_ja004_ja005

Model card Files Files and versions Metrics Training metrics Community

Akjava commited on Sep 14

Commit

6202dbd

•

1 Parent(s): 436546f

Update README.md

Files changed (1) hide show

README.md +8 -3

README.md CHANGED Viewed

@@ -3,9 +3,14 @@ license: mit
 language:
 - ja
 ---
-## FAILD
-merged model
-## Train(2024-09-14_04-08-31 )
 Not listen all checkpoint but this speak just separated voices
 - The train and valid split is based on word length and mora balance v1 (80:20).

 language:
 - ja
 ---
+trying merged model ja004 and ja005 ratio almost (3:2)
+## Final Result: FAILD
+voice is not merged,most of them ja004 voice,but sometime speak ja005
+## Train
+### Stage1
+seems just echo
+### Stage2 (2024-09-14_04-08-31 )
 Not listen all checkpoint but this speak just separated voices
 - The train and valid split is based on word length and mora balance v1 (80:20).