[PR #96] [MERGED] Restored speech recognition streaming mode as an independant module. #187

New issue

Closed

opened 2026-10-15 18:05:24 +00:00 by bsakaguchi · 0 comments

bsakaguchi commented

2026-10-15 18:05:24 +00:00

Owner

📋 Pull Request Information

Original PR: https://github.com/SillyTavern/SillyTavern-Extras/pull/96
Author: @Tony-sama
Created: 7/31/2023
Status: ✅ Merged
Merged: 7/31/2023
Merged by: @Cohee1207

Base: neo ← Head: neo

📝 Commits (1)

912c433 Restored speech recognition streaming mode as an independant module. Perform audio recording using mic on server side, detect voice start/end with vosk and transcript with whisper.

📊 Changes

3 files changed (+135 additions, -3 deletions)

View changed files

➕ modules/speech_recognition/streaming_module.py (+121 -0)
📝 modules/speech_recognition/whisper_module.py (+0 -1)
📝 server.py (+14 -2)

📄 Description

Perform audio recording using mic on server side, detect voice start/end with vosk and transcript with whisper.
Only usefull for user running extras on their local machine but allow interaction without requiring focus on ST.
Does not interfer with other speech recognition modules.

_{🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.}

## 📋 Pull Request Information **Original PR:** https://github.com/SillyTavern/SillyTavern-Extras/pull/96 **Author:** [@Tony-sama](https://github.com/Tony-sama) **Created:** 7/31/2023 **Status:** ✅ Merged **Merged:** 7/31/2023 **Merged by:** [@Cohee1207](https://github.com/Cohee1207) **Base:** `neo` ← **Head:** `neo` --- ### 📝 Commits (1) - [`912c433`](https://github.com/SillyTavern/SillyTavern-Extras/commit/912c4335c2e1d75a7042448bdbb0f1296db535ef) Restored speech recognition streaming mode as an independant module. Perform audio recording using mic on server side, detect voice start/end with vosk and transcript with whisper. ### 📊 Changes **3 files changed** (+135 additions, -3 deletions) <details> <summary>View changed files</summary> ➕ `modules/speech_recognition/streaming_module.py` (+121 -0) 📝 `modules/speech_recognition/whisper_module.py` (+0 -1) 📝 `server.py` (+14 -2) </details> ### 📄 Description Perform audio recording using mic on server side, detect voice start/end with vosk and transcript with whisper. Only usefull for user running extras on their local machine but allow interaction without requiring focus on ST. Does not interfer with other speech recognition modules. --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>

bsakaguchi

2026-10-15 18:05:24 +00:00