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(xtts): show manual inference with default speakers

This commit is contained in:
Enno Hermann 2024-12-17 10:41:49 +01:00
parent 9d5fc60a5d
commit 1f9dda65ad
1 changed files with 12 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

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

@ -163,12 +163,13 @@ from TTS.api import TTS
tts = TTS("tts_models/multilingual/multi-dataset/xtts_v2").to("cuda") tts = TTS("tts_models/multilingual/multi-dataset/xtts_v2").to("cuda")
# generate speech by cloning a voice using default settings # 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.", 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.",
file_path="output.wav", file_path="output.wav",
speaker="Ana Florence", speaker="Ana Florence",
language="en", language="en",
split_sentences=True split_sentences=True
) )
``` ```
@ -230,6 +231,11 @@ out = model.inference(
torchaudio.save("xtts.wav", torch.tensor(out["wav"]).unsqueeze(0), 24000) torchaudio.save("xtts.wav", torch.tensor(out["wav"]).unsqueeze(0), 24000)
``` ```
You can also use the Coqui speakers:
```python
gpt_cond_latent, speaker_embedding = model.speaker_manager.speakers["Ana Florence"].values()
```
#### Streaming manually #### Streaming manually