mARTin-B78/tts-dgx-spark-faster-qwen3-tts
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: clarify deterministic pt generation (v6.5.1)

Browse Source
This commit is contained in:
mARTin-B78 2026-06-21 00:53:05 +02:00
parent 7a8d8d17ad
commit 15f7fd63aa
1 changed files with 6 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
README.md
View File

@ -139,6 +139,8 @@ python config/auto_transcribe.py --api-url http://localhost:8010/v1/audio/transc
`config/generate_voices.py` runs automatically in the background, continuously watching your `speakers` directory. Whenever you add a new `.wav` and `.txt` file, it instantly updates `config/voices.json`. The API server hot-reloads the changes, meaning **you never need to restart the container when adding new voices!** `config/generate_voices.py` runs automatically in the background, continuously watching your `speakers` directory. Whenever you add a new `.wav` and `.txt` file, it instantly updates `config/voices.json`. The API server hot-reloads the changes, meaning **you never need to restart the container when adding new voices!**
When you start using a new voice for the first time, the server will automatically do the heavy lifting to extract the voice's acoustic fingerprint (a "speaker embedding") and save it as a `.pt` file in the `config/speakers/` directory. Future requests will instantly load this `.pt` file instead of re-analyzing the audio, which dramatically speeds up Time To First Audio (TTFA). When you start using a new voice for the first time, the server will automatically do the heavy lifting to extract the voice's acoustic fingerprint (a "speaker embedding") and save it as a `.pt` file in the `config/speakers/` directory. Future requests will instantly load this `.pt` file instead of re-analyzing the audio, which dramatically speeds up Time To First Audio (TTFA).
> **Note:** The generation of the `.pt` embedding is completely deterministic. Running the extraction process twice on the same reference `.wav` and `.txt` will yield the exact same fingerprint, so the resulting voice will not vary between regenerations.
## VoiceDesign voices ## VoiceDesign voices
VoiceDesign does not need reference audio. Define reusable voice personalities in `config/voicedesign_voices.json`: VoiceDesign does not need reference audio. Define reusable voice personalities in `config/voicedesign_voices.json`:
@ -341,6 +343,10 @@ The first request after container startup can be slower because CUDA graph captu
## Changelog ## Changelog
### v6.5.1 — 2026-06-21
**Documentation Update**
- Added documentation explicitly clarifying that `.pt` speaker embedding generation is fully deterministic and does not produce variable voice characteristics across restarts.
### v6.5 — 2026-06-20 ### v6.5 — 2026-06-20
**Feature: True Zero-Downtime Voice Hot-Reloading** **Feature: True Zero-Downtime Voice Hot-Reloading**