[PR #449] [MERGED] feat: Embed on-instance Whisper model for audio/mp4 transcribing #3360

Closed
opened 2026-02-22 18:33:37 -05:00 by yindo · 0 comments
Owner

📋 Pull Request Information

Original PR: https://github.com/Mintplex-Labs/anything-llm/pull/449
Author: @timothycarambat
Created: 12/15/2023
Status: Merged
Merged: 12/15/2023
Merged by: @timothycarambat

Base: masterHead: 329-embedded-whisper-audio


📝 Commits (6)

  • be15139 feat: Embed on-instance Whisper model for audio/mp4 transcribing
  • 51675f9 additional logging
  • b638491 add placeholder for tmp folder in collector storage
  • ffd0fd6 update README
  • 638dd79 update model size
  • 1cee598 update supported filetypes

📊 Changes

12 files changed (+636 additions, -64 deletions)

View changed files

📝 collector/index.js (+2 -0)
📝 collector/package.json (+5 -2)
collector/processSingleFile/convert/asAudio.js (+146 -0)
collector/storage/.gitignore (+2 -0)
collector/storage/tmp/.placeholder (+0 -0)
collector/utils/WhisperProviders/localWhisper.js (+59 -0)
collector/utils/asDocx.js (+0 -50)
📝 collector/utils/constants.js (+11 -0)
📝 collector/utils/files/index.js (+40 -0)
📝 collector/yarn.lock (+365 -10)
📝 frontend/src/components/Modals/MangeWorkspace/Documents/UploadFile/index.jsx (+1 -2)
📝 server/storage/models/README.md (+5 -0)

📄 Description

resolves #329


🔄 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/Mintplex-Labs/anything-llm/pull/449 **Author:** [@timothycarambat](https://github.com/timothycarambat) **Created:** 12/15/2023 **Status:** ✅ Merged **Merged:** 12/15/2023 **Merged by:** [@timothycarambat](https://github.com/timothycarambat) **Base:** `master` ← **Head:** `329-embedded-whisper-audio` --- ### 📝 Commits (6) - [`be15139`](https://github.com/Mintplex-Labs/anything-llm/commit/be1513952a5044a8c3fac3cfae87a810a2acf1d4) feat: Embed on-instance Whisper model for audio/mp4 transcribing - [`51675f9`](https://github.com/Mintplex-Labs/anything-llm/commit/51675f9e9031018684a233eaa4aab00b8e0c8e7a) additional logging - [`b638491`](https://github.com/Mintplex-Labs/anything-llm/commit/b638491d00ce3ecb7bd85f6acc0db6377562bf49) add placeholder for tmp folder in collector storage - [`ffd0fd6`](https://github.com/Mintplex-Labs/anything-llm/commit/ffd0fd6039be56c84ec16c84f7977dd5299cff60) update README - [`638dd79`](https://github.com/Mintplex-Labs/anything-llm/commit/638dd79231f0aa1f1d5a70a2210173c3b691e1c5) update model size - [`1cee598`](https://github.com/Mintplex-Labs/anything-llm/commit/1cee5985087ec9cf71fc0f18aba226d0079bfb9a) update supported filetypes ### 📊 Changes **12 files changed** (+636 additions, -64 deletions) <details> <summary>View changed files</summary> 📝 `collector/index.js` (+2 -0) 📝 `collector/package.json` (+5 -2) ➕ `collector/processSingleFile/convert/asAudio.js` (+146 -0) ➕ `collector/storage/.gitignore` (+2 -0) ➕ `collector/storage/tmp/.placeholder` (+0 -0) ➕ `collector/utils/WhisperProviders/localWhisper.js` (+59 -0) ➖ `collector/utils/asDocx.js` (+0 -50) 📝 `collector/utils/constants.js` (+11 -0) 📝 `collector/utils/files/index.js` (+40 -0) 📝 `collector/yarn.lock` (+365 -10) 📝 `frontend/src/components/Modals/MangeWorkspace/Documents/UploadFile/index.jsx` (+1 -2) 📝 `server/storage/models/README.md` (+5 -0) </details> ### 📄 Description resolves #329 --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
yindo added the pull-request label 2026-02-22 18:33:37 -05:00
yindo closed this issue 2026-02-22 18:33:37 -05:00
yindo changed title from [PR #449] feat: Embed on-instance Whisper model for audio/mp4 transcribing to [PR #449] [MERGED] feat: Embed on-instance Whisper model for audio/mp4 transcribing 2026-06-05 15:13:00 -04:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Mintplex-Labs/anything-llm#3360