RASPIAUDIO commited on
Commit
3e1ea4f
·
1 Parent(s): 62a0088

french version 1

Browse files
Files changed (1) hide show
  1. app.py +3 -9
app.py CHANGED
@@ -92,7 +92,7 @@ F5TTS_model_cfg = dict(
92
  E2TTS_model_cfg = dict(dim=1024, depth=24, heads=16, ff_mult=4)
93
 
94
  F5TTS_ema_model = load_model(
95
- "Gregniuki", "F5-tts_English_German_Polish", "Polish", DiT, F5TTS_model_cfg, 500000
96
  )
97
  #E2TTS_ema_model = load_model(
98
  # "SWivid", "F5-TTS", "E2TTS_Base", UNetT, E2TTS_model_cfg, 1200000
@@ -759,7 +759,7 @@ This is a local web UI for F5 TTS with advanced batch processing support. This a
759
  * [F5-TTS](https://arxiv.org/abs/2410.06885) (A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching)
760
  * [E2 TTS](https://arxiv.org/abs/2406.18009) (Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS)
761
 
762
- The checkpoint support Polish English and German.
763
 
764
  Generations using CPU takes usually 2-3 minutes
765
 
@@ -768,13 +768,7 @@ If you're having issues, try converting your reference audio to WAV or MP3, clip
768
  **NOTE: Reference text will be automatically transcribed with Whisper if not provided. For best results, keep your reference clips short (<15s). Ensure the audio is fully uploaded before generating.**
769
  """
770
  )
771
- gr.HTML(
772
- """
773
- <a href="https://www.buymeacoffee.com/gregniuki" target="_blank">
774
- <img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" alt="Buy Me A Coffee" style="height: 60px !important;width: 217px !important;">
775
- </a>
776
- """
777
- )
778
  gr.TabbedInterface([app_tts, app_podcast, app_emotional, app_credits], ["TTS", "Podcast", "Multi-Style", "Credits"])
779
 
780
  @click.command()
 
92
  E2TTS_model_cfg = dict(dim=1024, depth=24, heads=16, ff_mult=4)
93
 
94
  F5TTS_ema_model = load_model(
95
+ "RASPIAUDIO", "F5-French-MixedSpeakers-reduced", "model_last_reduced.pt", DiT, F5TTS_model_cfg, 500000
96
  )
97
  #E2TTS_ema_model = load_model(
98
  # "SWivid", "F5-TTS", "E2TTS_Base", UNetT, E2TTS_model_cfg, 1200000
 
759
  * [F5-TTS](https://arxiv.org/abs/2410.06885) (A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching)
760
  * [E2 TTS](https://arxiv.org/abs/2406.18009) (Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS)
761
 
762
+ The checkpoint support French
763
 
764
  Generations using CPU takes usually 2-3 minutes
765
 
 
768
  **NOTE: Reference text will be automatically transcribed with Whisper if not provided. For best results, keep your reference clips short (<15s). Ensure the audio is fully uploaded before generating.**
769
  """
770
  )
771
+
 
 
 
 
 
 
772
  gr.TabbedInterface([app_tts, app_podcast, app_emotional, app_credits], ["TTS", "Podcast", "Multi-Style", "Credits"])
773
 
774
  @click.command()