neonbjb/tortoise-tts
1
0
Fork 0
mirror of https://github.com/neonbjb/tortoise-tts.git synced 2026-02-02 05:44:23 +01:00
Code Issues Actions Packages Projects Releases Wiki Activity

Merge branch 'main' of https://github.com/neonbjb/tortoise-tts into main

Browse source
This commit is contained in:
manmay-nakhashi 2023-07-26 01:29:40 +05:30
parent c4b5bcf3db 3796069550
commit 8b317ebedf
2 changed files with 31 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

30
README.md
View file

@ -112,6 +112,36 @@ tts = api.TextToSpeech()
pcm_audio = tts.tts_with_preset("your text here", voice_samples=reference_clips, preset='fast')
```
To use deepspeed:
```python
reference_clips = [utils.audio.load_audio(p, 22050) for p in clips_paths]
tts = api.TextToSpeech(use_deepspeed=True)
pcm_audio = tts.tts_with_preset("your text here", voice_samples=reference_clips, preset='fast')
```
To use kv cache:
```python
reference_clips = [utils.audio.load_audio(p, 22050) for p in clips_paths]
tts = api.TextToSpeech(kv_cache=True)
pcm_audio = tts.tts_with_preset("your text here", voice_samples=reference_clips, preset='fast')
```
To run model in float16:
```python
reference_clips = [utils.audio.load_audio(p, 22050) for p in clips_paths]
tts = api.TextToSpeech(half=True)
pcm_audio = tts.tts_with_preset("your text here", voice_samples=reference_clips, preset='fast')
```
for Faster runs use all three:
```python
reference_clips = [utils.audio.load_audio(p, 22050) for p in clips_paths]
tts = api.TextToSpeech(use_deepspeed=True, kv_cache=True, half=True)
pcm_audio = tts.tts_with_preset("your text here", voice_samples=reference_clips, preset='fast')
```
## Voice customization guide
Tortoise was specifically trained to be a multi-speaker model. It accomplishes this by consulting reference clips.

2
setup.py
View file

@ -6,7 +6,7 @@ with open("README.md", "r", encoding="utf-8") as fh:
setuptools.setup(
name="TorToiSe",
packages=setuptools.find_packages(),
version="2.4.2",
version="2.5.0",
author="James Betker",
author_email="james@adamant.ai",
description="A high quality multi-voice text-to-speech library",