Hugging Face's logo

Spaces:
catactivationsound
/
speech-to-speech-translation
Build error

App Files Community
catactivationsound commited on
Commit
fbd1328
·
1 Parent(s): 4d6948b

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +1 -1
app.py CHANGED
@@ -43,7 +43,7 @@ title = "Cascaded STST"
43
  description = """
44
  Demo for cascaded speech-to-speech translation (STST), mapping from source speech in any language to target speech in English.
45
  Demo uses OpenAI's [Whisper Base](https://huggingface.co/openai/whisper-base) model for speech translation,
46
- and a [finetuned version](https://huggingface.co/sanchit-gandhi/speecht5_tts_vox_nl)
47
  of Microsoft's [SpeechT5 TTS](https://huggingface.co/microsoft/speecht5_tts) for text-to-speech:
48
 
49
  ![Cascaded STST](https://huggingface.co/datasets/huggingface-course/audio-course-images/resolve/main/s2st_cascaded.png "Diagram of cascaded speech to speech translation")
 
43
  description = """
44
  Demo for cascaded speech-to-speech translation (STST), mapping from source speech in any language to target speech in English.
45
  Demo uses OpenAI's [Whisper Base](https://huggingface.co/openai/whisper-base) model for speech translation,
46
+ and a [finetuned version](https://huggingface.co/catactivationsound/speecht5_finetuned_voxpopuli_hu)
47
  of Microsoft's [SpeechT5 TTS](https://huggingface.co/microsoft/speecht5_tts) for text-to-speech:
48
 
49
  ![Cascaded STST](https://huggingface.co/datasets/huggingface-course/audio-course-images/resolve/main/s2st_cascaded.png "Diagram of cascaded speech to speech translation")