feat: add faster-whisper and local Whisper support#53
Open
oxbar wants to merge 3 commits into
Open
Conversation
This commit introduces a unified transcript provider system, allowing users to choose between three transcription backends: local OpenAI Whisper, faster-whisper, and AssemblyAI. The default behavior uses AssemblyAI when its API key is present, otherwise falls back to local Whisper. Key changes: - Add TRANSCRIPT_PROVIDER environment variable to select transcription provider - Add new runtime settings for Whisper language, faster-whisper device and compute type - Update all project documentation including README, QUICKSTART and config docs - Add admin UI settings for all new configuration keys - Add comprehensive unit tests for provider selection and new backends - Refactor video utilities to support all three transcript providers - Maintain backward compatibility for existing WHISPER_MODEL_SIZE env var - Add faster-whisper Python dependency - Update mediapipe dependency constraints for non-linux aarch64 systems
|
Someone is attempting to deploy a commit to the Shiori LLC Team on Vercel. A member of the Team first needs to authorize it. |
added 2 commits
June 22, 2026 03:26
Add support for using OpenAI-compatible endpoints like vLLM by introducing the OPENAI_BASE_URL runtime configuration option. Changes include: - Register OPENAI_BASE_URL in runtime settings and environment processing - Add admin UI metadata for the new configuration setting - Update .env examples and docker-compose environment passing - Extend Config class to load and resolve the custom base URL - Modify AI model builder to use custom base URL for OpenAI providers - Add unit tests for the new config and model loading logic - Update documentation across README, QUICKSTART, and configuration docs
use faster_whisper + Ollama qwen2.5:7b as the recommended local self-hosted setup, replace the previous Google Gemini default, adjust default processing parameters, update environment variable defaults, and refresh troubleshooting guidance
oxbar
marked this pull request as draft
June 24, 2026 19:58
oxbar
marked this pull request as ready for review
June 24, 2026 19:58
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This commit introduces a unified transcript provider system, allowing users to choose between three transcription backends: local OpenAI Whisper, faster-whisper, and AssemblyAI. The default behavior uses AssemblyAI when its API key is present, otherwise falls back to local Whisper.
Key changes: