[PR #247] [MERGED] Implementation for faster-whisper #246

New issue

Closed

opened 2026-10-15 18:05:53 +00:00 by bsakaguchi · 0 comments

bsakaguchi commented

2026-10-15 18:05:53 +00:00

Owner

📋 Pull Request Information

Original PR: https://github.com/SillyTavern/SillyTavern-Extras/pull/247
Author: @ArrangingFear56
Created: 12/9/2024
Status: ✅ Merged
Merged: 12/10/2024
Merged by: @Cohee1207

Base: main ← Head: main

📝 Commits (10+)

9d55444 Add files via upload
5903207 Delete whisper_module.py
24d025a Add files via upload
ea996b1 Delete modules/whisper_module.py
2fbbe98 Add files via upload
6b3c1a3 Update fasterWhisperRequirements.txt
23e8a2c Revert "Add files via upload"
f3cb6c3 Update whisper_module.py
2ef3724 Revert "Update whisper_module.py"
dbec27b added arguments for faster-whisper usage without breaking original whisper implementation

📊 Changes

5 files changed (+117 additions, -4 deletions)

View changed files

📝 .gitignore (+1 -0)
📝 README.md (+13 -0)
➕ modules/speech_recognition/faster_whisper_module.py (+66 -0)
➕ requirements-faster-whisper.txt (+7 -0)
📝 server.py (+30 -4)

📄 Description

Updates whisper(extras) to use faster-whisper instead of openAI-whisper, defaults to large-v3-turbo model, install CUDA 12 and cuDNN 8, then run pip install -r whisperRequirements.txt to finish installation.

_{🔄 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/247 **Author:** [@ArrangingFear56](https://github.com/ArrangingFear56) **Created:** 12/9/2024 **Status:** ✅ Merged **Merged:** 12/10/2024 **Merged by:** [@Cohee1207](https://github.com/Cohee1207) **Base:** `main` ← **Head:** `main` --- ### 📝 Commits (10+) - [`9d55444`](https://github.com/SillyTavern/SillyTavern-Extras/commit/9d55444995a93aba06fae10bcff6e65d3f3e6e88) Add files via upload - [`5903207`](https://github.com/SillyTavern/SillyTavern-Extras/commit/590320728152f5c0228a1667dd1e8c290148f8de) Delete whisper_module.py - [`24d025a`](https://github.com/SillyTavern/SillyTavern-Extras/commit/24d025af0b2ed528e8e418b91dc9bfaf19617c46) Add files via upload - [`ea996b1`](https://github.com/SillyTavern/SillyTavern-Extras/commit/ea996b19571705fbd3db42852980e8b57a834eea) Delete modules/whisper_module.py - [`2fbbe98`](https://github.com/SillyTavern/SillyTavern-Extras/commit/2fbbe98eda5dc4a92a8a5a4dbdb8a5578e106eeb) Add files via upload - [`6b3c1a3`](https://github.com/SillyTavern/SillyTavern-Extras/commit/6b3c1a3dd24d439bbd8d581520773f655aa571a3) Update fasterWhisperRequirements.txt - [`23e8a2c`](https://github.com/SillyTavern/SillyTavern-Extras/commit/23e8a2cf43da6b099deb2a4d5c85a9a8303febf7) Revert "Add files via upload" - [`f3cb6c3`](https://github.com/SillyTavern/SillyTavern-Extras/commit/f3cb6c330b6c1bcabd55fca8b56f9f2dbdf97e56) Update whisper_module.py - [`2ef3724`](https://github.com/SillyTavern/SillyTavern-Extras/commit/2ef37240b90d0abecc81f4d2b575843f0140626a) Revert "Update whisper_module.py" - [`dbec27b`](https://github.com/SillyTavern/SillyTavern-Extras/commit/dbec27b18a5613a9e1c46bf00a9e6efc9b12f7b7) added arguments for faster-whisper usage without breaking original whisper implementation ### 📊 Changes **5 files changed** (+117 additions, -4 deletions) <details> <summary>View changed files</summary> 📝 `.gitignore` (+1 -0) 📝 `README.md` (+13 -0) ➕ `modules/speech_recognition/faster_whisper_module.py` (+66 -0) ➕ `requirements-faster-whisper.txt` (+7 -0) 📝 `server.py` (+30 -4) </details> ### 📄 Description Updates whisper(extras) to use faster-whisper instead of openAI-whisper, defaults to large-v3-turbo model, install CUDA 12 and cuDNN 8, then run `pip install -r whisperRequirements.txt` to finish installation. --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>

bsakaguchi

2026-10-15 18:05:53 +00:00