facebook

/

mms-tts-eng

like 150

Follow

AI at Meta 6.93k

If you just want to synthesize audio, you only need 5 lines of code. 1 line: from transformers import pipeline 2 line: import scipy 3 line: pipe = pipeline("text-to-speech", model="facebook/mms-tts-eng", device=0) 4 line: results = pipe("your text") 5 line: scipy.io.wavfile.write("audio_vits.wav", rate=results["sampling_rate"], data=results["audio"].squeeze())

PS:
Create a text file and paste the code into it. Then change its extension from "txt" to "py". Python only runs scripts with the extension "py". You need Python and the necessary libraries installed (transformers, torch==2.0.1, torchvision==0.15.2, torchaudio==2.0.2 and phonemizer).