igna/LuxTTS
1
0
Fork 0
Code Activity

fix example for undefined variables and runnin not on notebook

Browse Source
This commit is contained in:
kishida
2026-01-26 15:20:29 +09:00
parent 6c9979e6ab
commit 1e9ceb0ca7
1 changed files with 7 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
README.md
View File

@@ -57,14 +57,15 @@ prompt_audio = 'audio_file.wav'
encoded_prompt = lux_tts.encode_prompt(prompt_audio, rms=0.01)
## generate speech
final_wav = lux_tts.generate_speech(text, encoded_prompt, num_steps=num_steps)
final_wav = lux_tts.generate_speech(text, encoded_prompt, num_steps=4)
## save audio
final_wav = final_wav.numpy().squeeze()
sf.write('output.wav', audio_data, 48000)
sf.write('output.wav', final_wav, 48000)
## display speech
display(Audio(final_wav, rate=48000))
if display is not None:
display(Audio(final_wav, rate=48000))
```
#### Inference with sampling params:
@@ -92,10 +93,11 @@ final_wav = lux_tts.generate_speech(text, encoded_prompt, num_steps=num_steps, t
## save audio
final_wav = final_wav.numpy().squeeze()
sf.write('output.wav', audio_data, 48000)
sf.write('output.wav', final_wav, 48000)
## display speech
display(Audio(final_wav, rate=48000))
if display is not None:
display(Audio(final_wav, rate=48000))
```
## Tips
- Please use at minimum a 3 second audio file for voice cloning.