Hugging Face's logo

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

App Files Community
ezrab commited on
Commit
dcf1918
·
verified ·
1 Parent(s): 03fb77c

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +2 -2
app.py CHANGED
@@ -39,8 +39,8 @@ def speech_to_speech_translation(audio):
39
 
40
  title = "Cascaded STST"
41
  description = """
42
- Demo for cascaded speech-to-speech translation (STST), mapping from source speech in any language to target speech in Spanish. Demo uses OpenAI's [Whisper Base](https://huggingface.co/openai/whisper-base) model for speech translation, and Microsoft's
43
- [SpeechT5 TTS](https://huggingface.co/microsoft/speecht5_tts) model for text-to-speech:
44
 
45
  ![Cascaded STST](https://huggingface.co/datasets/huggingface-course/audio-course-images/resolve/main/s2st_cascaded.png "Diagram of cascaded speech to speech translation")
46
  """
 
39
 
40
  title = "Cascaded STST"
41
  description = """
42
+ Demo for cascaded speech-to-speech translation (STST), mapping from source speech in any language to target speech in Spanish. Demo uses OpenAI's [Whisper Base](https://huggingface.co/openai/whisper-base) model for speech translation, and Facebook's
43
+ [MMS TTS](https://huggingface.co/facebook/mms-tts-spa) model for text-to-speech:
44
 
45
  ![Cascaded STST](https://huggingface.co/datasets/huggingface-course/audio-course-images/resolve/main/s2st_cascaded.png "Diagram of cascaded speech to speech translation")
46
  """