Medix-AI/coqui-tts
Medix-AI
/
coqui-tts
mirror of https://github.com/coqui-ai/TTS.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #602 from thorstenMueller/dev 

Increase robustness in synthesize with wavegrad model
This commit is contained in:
Eren Gölge 2020-12-21 09:51:03 +01:00 committed by GitHub
parent f0f652e122 f673f8f74d
commit 4cfde34ad8
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 10 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
TTS/bin/synthesize.py
View File

@ -37,7 +37,16 @@ def tts(model, vocoder_model, text, CONFIG, use_cuda, ap, use_gl, speaker_fileid
if CONFIG.model == "Tacotron" and not use_gl:
mel_postnet_spec = ap.out_linear_to_mel(mel_postnet_spec.T).T
if not use_gl:
waveform = vocoder_model.inference(torch.FloatTensor(mel_postnet_spec.T).unsqueeze(0))
# Use if not computed noise schedule with tune_wavegrad
beta = np.linspace(1e-6, 0.01, 50)
vocoder_model.compute_noise_level(beta)
# Use alternative when using output npy file from tune_wavegrad
# beta = np.load("output-tune-wavegrad.npy", allow_pickle=True).item()
# vocoder_model.compute_noise_level(beta['beta'])
device_type = "cuda" if use_cuda else "cpu"
waveform = vocoder_model.inference(torch.FloatTensor(mel_postnet_spec.T).to(device_type).unsqueeze(0))
if use_cuda and not use_gl:
waveform = waveform.cpu()
if not use_gl: