Jarod/tortoise-tts
1
1
Fork 0
forked from mrq/tortoise-tts
Code Pull Requests Activity

read.py combines all candidates

Browse Source 
If candidates where greater than 1 on in read.py, only the fist candidate clips would be combined. This adds a bit of code to make a combined file for every candidate.
This commit is contained in:
Marcus Llewellyn 2022-06-04 17:47:29 -05:00
parent e574f19fc9
commit 5a74461c1e
1 changed files with 13 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
tortoise/read.py
View File

@ -72,11 +72,22 @@ if __name__ == '__main__':
gen = gen[0].squeeze(0).cpu()
all_parts.append(gen)
full_audio = torch.cat(all_parts, dim=-1)
torchaudio.save(os.path.join(voice_outpath, 'combined.wav'), full_audio, 24000)
if args.candidates == 1:
full_audio = torch.cat(all_parts, dim=-1)
torchaudio.save(os.path.join(voice_outpath, 'combined.wav'), full_audio, 24000)
if args.produce_debug_state:
os.makedirs('debug_states', exist_ok=True)
dbg_state = (seed, texts, voice_samples, conditioning_latents)
torch.save(dbg_state, f'debug_states/read_debug_{selected_voice}.pth')
# Combine each candidate's audio clips.
if args.candidates > 1:
audio_clips = []
for candidate in range(args.candidates):
for line in range(len(texts)):
wav_file = os.path.join(voice_outpath, str(line), f"{candidate}.wav")
audio_clips.append(load_audio(wav_file, 24000))
audio_clips = torch.cat(audio_clips, dim=-1)
torchaudio.save(os.path.join(voice_outpath, f"combined_{candidate:02d}.wav"), audio_clips, 24000)
audio_clips = []