wassname/TTS
1
0
Fork 0
mirror of https://github.com/wassname/TTS.git synced 2026-09-09 11:16:00 +08:00
Code Issues Packages Projects Releases Wiki Activity

Added support for npy output from tune-wavegrad

Browse Source
This commit is contained in:
Thorsten Mueller
2020-12-19 22:51:22 +01:00
parent 2aa0354b44
commit f673f8f74d
1 changed files with 5 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
TTS/bin/synthesize.py
+5
View File
@@ -37,8 +37,13 @@ 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:
# 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))