From ff84654b2a9e75195f9ba5da32aa61d3652651f3 Mon Sep 17 00:00:00 2001 From: manmay nakhashi Date: Sun, 16 Jul 2023 16:41:49 +0530 Subject: [PATCH 1/2] Update README.md --- README.md | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) diff --git a/README.md b/README.md index 707dfde..dde30d8 100644 --- a/README.md +++ b/README.md @@ -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. From 799c5d261a9507e984e857a0c05ffe8fcc23ce29 Mon Sep 17 00:00:00 2001 From: Roberts Slisans Date: Wed, 19 Jul 2023 10:48:52 +0300 Subject: [PATCH 2/2] bump minor version in setup.py --- setup.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/setup.py b/setup.py index 2a9044a..ad24cea 100644 --- a/setup.py +++ b/setup.py @@ -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",