Medix-AI/coqui-tts
Medix-AI
/
coqui-tts
mirror of https://github.com/coqui-ai/TTS.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

docs: use .to("cuda") instead of deprecated gpu=True

This commit is contained in:
Enno Hermann 2024-12-03 22:06:39 +01:00
parent 8241d55e70
commit 8c381e3e48
3 changed files with 11 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
TTS/api.py
View File

@ -35,21 +35,21 @@ class TTS(nn.Module):
>>> tts.tts_to_file(text="Hello world!", speaker=tts.speakers[0], language=tts.languages[0], file_path="output.wav")
Example with a single-speaker model:
>>> tts = TTS(model_name="tts_models/de/thorsten/tacotron2-DDC", progress_bar=False, gpu=False)
>>> tts = TTS(model_name="tts_models/de/thorsten/tacotron2-DDC", progress_bar=False)
>>> tts.tts_to_file(text="Ich bin eine Testnachricht.", file_path="output.wav")
Example loading a model from a path:
>>> tts = TTS(model_path="/path/to/checkpoint_100000.pth", config_path="/path/to/config.json", progress_bar=False, gpu=False)
>>> tts = TTS(model_path="/path/to/checkpoint_100000.pth", config_path="/path/to/config.json", progress_bar=False)
>>> tts.tts_to_file(text="Ich bin eine Testnachricht.", file_path="output.wav")
Example voice cloning with YourTTS in English, French and Portuguese:
>>> tts = TTS(model_name="tts_models/multilingual/multi-dataset/your_tts", progress_bar=False, gpu=True)
>>> tts = TTS(model_name="tts_models/multilingual/multi-dataset/your_tts", progress_bar=False).to("cuda")
>>> tts.tts_to_file("This is voice cloning.", speaker_wav="my/cloning/audio.wav", language="en", file_path="thisisit.wav")
>>> tts.tts_to_file("C'est le clonage de la voix.", speaker_wav="my/cloning/audio.wav", language="fr", file_path="thisisit.wav")
>>> tts.tts_to_file("Isso é clonagem de voz.", speaker_wav="my/cloning/audio.wav", language="pt", file_path="thisisit.wav")
Example Fairseq TTS models (uses ISO language codes in https://dl.fbaipublicfiles.com/mms/tts/all-tts-languages.html):
>>> tts = TTS(model_name="tts_models/eng/fairseq/vits", progress_bar=False, gpu=True)
>>> tts = TTS(model_name="tts_models/eng/fairseq/vits", progress_bar=False).to("cuda")
>>> tts.tts_to_file("This is a test.", file_path="output.wav")
Args:

4
docs/source/models/bark.md
View File

@ -37,7 +37,7 @@ from TTS.api import TTS
# Load the model to GPU
# Bark is really slow on CPU, so we recommend using GPU.
tts = TTS("tts_models/multilingual/multi-dataset/bark", gpu=True)
tts = TTS("tts_models/multilingual/multi-dataset/bark").to("cuda")
# Cloning a new speaker
@ -57,7 +57,7 @@ tts.tts_to_file(text="Hello, my name is Manmay , how are you?",
# random speaker
tts = TTS("tts_models/multilingual/multi-dataset/bark", gpu=True)
tts = TTS("tts_models/multilingual/multi-dataset/bark").to("cuda")
tts.tts_to_file("hello world", file_path="out.wav")
```

10
docs/source/models/xtts.md
View File

@ -118,7 +118,7 @@ You can optionally disable sentence splitting for better coherence but more VRAM
```python
from TTS.api import TTS
tts = TTS("tts_models/multilingual/multi-dataset/xtts_v2", gpu=True)
tts = TTS("tts_models/multilingual/multi-dataset/xtts_v2").to("cuda")
# generate speech by cloning a voice using default settings
tts.tts_to_file(text="It took me quite a long time to develop a voice, and now that I have it I'm not going to be silent.",
@ -137,15 +137,15 @@ You can pass multiple audio files to the `speaker_wav` argument for better voice
from TTS.api import TTS
# using the default version set in 🐸TTS
tts = TTS("tts_models/multilingual/multi-dataset/xtts_v2", gpu=True)
tts = TTS("tts_models/multilingual/multi-dataset/xtts_v2").to("cuda")
# using a specific version
# 👀 see the branch names for versions on https://huggingface.co/coqui/XTTS-v2/tree/main
# ❗some versions might be incompatible with the API
tts = TTS("xtts_v2.0.2", gpu=True)
tts = TTS("xtts_v2.0.2").to("cuda")
# getting the latest XTTS_v2
tts = TTS("xtts", gpu=True)
tts = TTS("xtts").to("cuda")
# generate speech by cloning a voice using default settings
tts.tts_to_file(text="It took me quite a long time to develop a voice, and now that I have it I'm not going to be silent.",
@ -160,7 +160,7 @@ You can do inference using one of the available speakers using the following cod
```python
from TTS.api import TTS
tts = TTS("tts_models/multilingual/multi-dataset/xtts_v2", gpu=True)
tts = TTS("tts_models/multilingual/multi-dataset/xtts_v2").to("cuda")
# generate speech by cloning a voice using default settings
tts.tts_to_file(text="It took me quite a long time to develop a voice, and now that I have it I'm not going to be silent.",