Hugging Face's logo

Spaces:
zongxiao
/
speech-to-speech
Paused

App Files Community
zongxiao commited on
Commit
258dcc3
·
1 Parent(s): 303dd67

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +1 -1
app.py CHANGED
@@ -34,7 +34,7 @@ def speech_to_speech_translation(audio,voice_preset="v2/zh_speaker_1"):
34
  synthesised_speech = (synthesised_speech.numpy() * 32767).astype(np.int16)
35
  return (synthesised_rate , synthesised_speech.T),translated_text,label_outputs
36
 
37
- title = "Multilanguage to Chinese(mandarin) Cascaded STST"
38
  description = """
39
  Demo for cascaded speech-to-speech translation (STST), mapping from source speech in Multilanguage to target speech in Chinese(mandarin). Demo uses OpenAI's [Whisper arge-v2](https://huggingface.co/openai/whisper-large-v2) model for speech translation, and a suno/bark[bark-small](https://huggingface.co/suno/bark) model for text-to-speech:
40
  ![Cascaded STST](https://huggingface.co/datasets/huggingface-course/audio-course-images/resolve/main/s2st_cascaded.png "Diagram of cascaded speech to speech translation")
 
34
  synthesised_speech = (synthesised_speech.numpy() * 32767).astype(np.int16)
35
  return (synthesised_rate , synthesised_speech.T),translated_text,label_outputs
36
 
37
+ title = "外国话转中文话"
38
  description = """
39
  Demo for cascaded speech-to-speech translation (STST), mapping from source speech in Multilanguage to target speech in Chinese(mandarin). Demo uses OpenAI's [Whisper arge-v2](https://huggingface.co/openai/whisper-large-v2) model for speech translation, and a suno/bark[bark-small](https://huggingface.co/suno/bark) model for text-to-speech:
40
  ![Cascaded STST](https://huggingface.co/datasets/huggingface-course/audio-course-images/resolve/main/s2st_cascaded.png "Diagram of cascaded speech to speech translation")