hynt
/

F5-TTS-Vietnamese-100h

Model card Files Files and versions

hynt commited on Apr 4

Commit

f662f70

·

verified ·

1 Parent(s): 3700ce2

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -29,7 +29,7 @@ A compact fine-tuned version of F5-TTS trained on 150 hours of Vietnamese speech
 ---
 ## 📌 Model Details
-- **Dataset:** VLSP 2021, VLSP 2022, VLSP 2023, vietTTS, TeacherDinh-UEH and some speech sources from YouTube channels.
 - **Total dataset durations:** 150 hours
 - **Data processing Technique:**
   - Remove all music background from audios, using facebook demucs model: https://github.com/facebookresearch/demucs

 ---
 ## 📌 Model Details
+- **Dataset:** VLSP 2021, VLSP 2022, VLSP 2023, VietTTS, TeacherDinh-UEH and some speech sources from YouTube channels.
 - **Total dataset durations:** 150 hours
 - **Data processing Technique:**
   - Remove all music background from audios, using facebook demucs model: https://github.com/facebookresearch/demucs