Hugging Face's logo

Spaces:
J3
/
speech-to-speech-translation
Sleeping

App Files Community
J3 commited on
Commit
1750312
·
1 Parent(s): 0d87935

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +1 -4
app.py CHANGED
@@ -48,10 +48,7 @@ def speech_to_speech_translation(audio):
48
 
49
  title = "Cascaded STST"
50
  description = """
51
- Demo for cascaded speech-to-speech translation (STST), mapping from source speech in any language to target speech in italian. Demo uses OpenAI's [Whisper Base](https://huggingface.co/openai/whisper-base) model for speech translation, and Microsoft's
52
- [SpeechT5 TTS](https://huggingface.co/microsoft/speecht5_tts) model for text-to-speech:
53
-
54
- ![Cascaded STST](https://huggingface.co/datasets/huggingface-course/audio-course-images/resolve/main/s2st_cascaded.png "Diagram of cascaded speech to speech translation")
55
  """
56
 
57
  demo = gr.Blocks()
 
48
 
49
  title = "Cascaded STST"
50
  description = """
51
+ Demo for cascaded speech-to-speech translation (STST), mapping from source speech in any language to target speech in italian.
 
 
 
52
  """
53
 
54
  demo = gr.Blocks()