valenti/spark-pocket-tts
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Default the English model's temperature to 0.3 (#223)

Browse Source 
## Motivation

Human evaluations consistently prefer the English model at temperature
**0.3** over the current default **0.7**, and the change is free on
every objective axis we measured.
This commit is contained in:
Manu Orsini
2026-07-16 14:42:04 +02:00
committed by GitHub
parent 9514983efd
commit d108410d23
7 changed files with 20 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/CLI Commands/generate.md
+1 -1
View File
@@ -25,7 +25,7 @@ This will generate a WAV file `./tts_output.wav` with the default text and voice
- `--config CONFIG_PATH`: Path to custom config.yaml (for loading local model files). Incompatible with `--language`.
- `--lsd-decode-steps LSD_DECODE_STEPS`: Number of generation steps (default: 1)
- `--temperature TEMPERATURE`: Temperature for generation (default: 0.7)
- `--temperature TEMPERATURE`: Temperature for generation (default: the model's recommended value from its config — 0.3 for the English model, 0.7 otherwise)
- `--noise-clamp NOISE_CLAMP`: Noise clamp value (default: None)
- `--eos-threshold EOS_THRESHOLD`: EOS threshold (default: -4.0)
- `--frames-after-eos FRAMES_AFTER_EOS`: Number of frames to generate after EOS (default: None, auto-calculated based on the text length). Each frame is 80ms.