Spaces:
Paused
Paused
Update app.py
Browse files
app.py
CHANGED
@@ -34,9 +34,9 @@ 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 = "
|
38 |
description = """
|
39 |
-
作为[Hugging Face Audio course](https://github.com/danfouer/HFAudioCourse)
|
40 |
|
41 |
![Cascaded STST](https://huggingface.co/datasets/huggingface-course/audio-course-images/resolve/main/s2st_cascaded.png "Diagram of cascaded speech to speech translation")
|
42 |
"""
|
|
|
34 |
synthesised_speech = (synthesised_speech.numpy() * 32767).astype(np.int16)
|
35 |
return (synthesised_rate , synthesised_speech.T),translated_text,label_outputs
|
36 |
|
37 |
+
title = "外国话转普通话"
|
38 |
description = """
|
39 |
+
作为[Hugging Face Audio course](https://github.com/danfouer/HFAudioCourse) 的结课大作业,本演示调用了三个自然语言处理的大模型,一个用于将外国话翻译成中文,一个用于判断说的哪个国家的话,一个用于将中文转成普通话语音输出。演示同时支持语音上传和麦克风输入,转换速度比较慢因为租不起GPU的服务器(支出增加20倍),建议您通过已经缓存Examples体验效果。欢迎添加我的微信号:ESGGTP 与我的平行人交流。
|
40 |
|
41 |
![Cascaded STST](https://huggingface.co/datasets/huggingface-course/audio-course-images/resolve/main/s2st_cascaded.png "Diagram of cascaded speech to speech translation")
|
42 |
"""
|