mrq/tortoise-tts
4
6
Fork 15
Code Issues 9 Pull Requests 1 Packages Projects Releases Wiki Activity

add regenerate option

Browse Source
This commit is contained in:
James Betker 2022-04-25 20:05:21 -06:00
parent e877af5b0f
commit d96d2bd76e
2 changed files with 15 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
README.md
View File

@ -44,10 +44,18 @@ python do_tts.py --text "I'm going to speak this" --voice dotrice --preset fast
### read.py ### read.py
This script provides tools for reading large amounts of text. This script provides tools for reading large amounts of text.
```shell ```shell
python read.py --textfile <your text to be read> --voice dotrice python read.py --textfile <your text to be read> --voice dotrice
``` ```
This will break up the textfile into sentences, and then convert them to speech one at a time. It will output a series
of spoken clips as they are generated. Once all the clips are generated, it will combine them into a single file and
output that as well.
Sometimes Tortoise screws up an output. You can re-generate any bad clips by re-running `read.py` with the --regenerate
argument.
### API ### API
Tortoise can be used programmatically, like so: Tortoise can be used programmatically, like so:

7
read.py
View File

@ -35,6 +35,7 @@ if __name__ == '__main__':
'Use the & character to join two voices together. Use a comma to perform inference on multiple voices.', default='patrick_stewart') 'Use the & character to join two voices together. Use a comma to perform inference on multiple voices.', default='patrick_stewart')
parser.add_argument('--output_path', type=str, help='Where to store outputs.', default='results/longform/') parser.add_argument('--output_path', type=str, help='Where to store outputs.', default='results/longform/')
parser.add_argument('--preset', type=str, help='Which voice preset to use.', default='standard') parser.add_argument('--preset', type=str, help='Which voice preset to use.', default='standard')
parser.add_argument('--regenerate', type=str, help='Comma-separated list of clip numbers to re-generate, or nothing.', default=None)
parser.add_argument('--voice_diversity_intelligibility_slider', type=float, parser.add_argument('--voice_diversity_intelligibility_slider', type=float,
help='How to balance vocal diversity with the quality/intelligibility of the spoken text. 0 means highly diverse voice (not recommended), 1 means maximize intellibility', help='How to balance vocal diversity with the quality/intelligibility of the spoken text. 0 means highly diverse voice (not recommended), 1 means maximize intellibility',
default=.5) default=.5)
@ -43,6 +44,9 @@ if __name__ == '__main__':
outpath = args.output_path outpath = args.output_path
voices = get_voices() voices = get_voices()
selected_voices = args.voice.split(',') selected_voices = args.voice.split(',')
regenerate = args.regenerate
if regenerate is not None:
regenerate = [int(e) for e in regenerate.split(',')]
for selected_voice in selected_voices: for selected_voice in selected_voices:
voice_outpath = os.path.join(outpath, selected_voice) voice_outpath = os.path.join(outpath, selected_voice)
os.makedirs(voice_outpath, exist_ok=True) os.makedirs(voice_outpath, exist_ok=True)
@ -71,6 +75,9 @@ if __name__ == '__main__':
conds.append(c) conds.append(c)
all_parts = [] all_parts = []
for j, text in enumerate(texts): for j, text in enumerate(texts):
if regenerate is not None and j not in regenerate:
all_parts.append(load_audio(os.path.join(voice_outpath, f'{j}.wav'), 24000))
continue
gen = tts.tts_with_preset(text, conds, preset=args.preset, clvp_cvvp_slider=args.voice_diversity_intelligibility_slider) gen = tts.tts_with_preset(text, conds, preset=args.preset, clvp_cvvp_slider=args.voice_diversity_intelligibility_slider)
gen = gen.squeeze(0).cpu() gen = gen.squeeze(0).cpu()
torchaudio.save(os.path.join(voice_outpath, f'{j}.wav'), gen, 24000) torchaudio.save(os.path.join(voice_outpath, f'{j}.wav'), gen, 24000)