Hugging Face's logo

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

App Files Community
hlumin commited on
Commit
ae92cbe
·
1 Parent(s): b888943

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +3 -4
app.py CHANGED
@@ -39,11 +39,10 @@ def speech_to_speech_translation(audio):
39
  return 16000, synthesised_speech
40
 
41
 
42
- 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. Demo uses OpenAI's [Whisper Base](https://huggingface.co/openai/whisper-base) model for speech translation, and Microsoft's
45
- [SpeechT5 TTS](https://huggingface.co/microsoft/speecht5_tts) model for text-to-speech:
46
-
47
  ![Cascaded STST](https://huggingface.co/datasets/huggingface-course/audio-course-images/resolve/main/s2st_cascaded.png "Diagram of cascaded speech to speech translation")
48
  """
49
 
 
39
  return 16000, synthesised_speech
40
 
41
 
42
+ title = "STST in LoFi Italian 😎"
43
  description = """
44
+ Demo for cascaded speech-to-speech translation (STST), mapping from source speech in any language to super lo-fi Italian speech . Demo uses OpenAI's [Whisper Base](https://huggingface.co/openai/whisper-base) model for speech translation, and Microsoft's
45
+ [SpeechT5 TTS](https://huggingface.co/microsoft/speecht5_tts) model poorly fine-tuned on the VoxPopuli italian subset for text-to-speech. But it kinda sounds like Italian folks, it kinda does:
 
46
  ![Cascaded STST](https://huggingface.co/datasets/huggingface-course/audio-course-images/resolve/main/s2st_cascaded.png "Diagram of cascaded speech to speech translation")
47
  """
48