Hugging Face's logo

Spaces:
TDN-M
/
text_to_speech_sync_video
Running

App Files Community
text_to_speech_sync_video / Wav2Lip /import_audio.py
zmbfeng's picture
zmbfeng
Wav2lip commits without big files
e22ac1d
raw
history blame
139 Bytes
import audio
wav = audio.load_wav("/content/gdrive/MyDrive/Avatar/chat_bot/audio/input_audio.wav", 16000)
mel = audio.melspectrogram(wav)