change the generized wav
Opened this issue · 1 comments
ffxz commented
i use the tts model, but the output wav is read by same person, i want to know how can i change the output frequency?
zabir-nabil commented
import soundfile as sf
data, samplerate1 = sf.read('generated.wav')
sf.write('new_gen.wav', data, samplerate2)
This is a dummy approach.
https://pysoundfile.readthedocs.io/en/0.9.0/
https://papers.nips.cc/paper/6889-deep-voice-2-multi-speaker-neural-text-to-speech.pdf