Feature/transcription language selection #55
Conversation
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
…S - Merge pull request #409 from rmusser01/dev ALL PRIOR VERSIONS ARE BROKEN BY THIS MERGE. THIS VERSION INTRODUCES A NEW config.txt FILE WHICH WILL CAUSE BREAKING WHEN USING ANY LLM API CALLS. Docs, TTS, answer streaming, web search and perplexity clone Updates: More Docs (no user guides yet 👎 , but we got some feature documentation! 👍 ) Foundation for TTS, setup a basic pipeline and have the ability/plan to add more TTS APIs/Engines Have support for streaming of answers in chat in all except the 4-way chat and the One prompt-mutiple, API chat. Added foundations + actual feature of Web Search, can now do web search + sub searches to answer a query/do research on a topic. UI is a (even more of a temporary) placeholder for now, not too happy with it. But the underlying pipeline is pretty nice, can do a single -> sub/split query through your choice of search provider (Bing, DDG, Google, Brave, SearX, Kagi) and then have the results evaluated for relevancy, collected via page scraping and then summarized for final analysis. Lots of areas for improvement.
config.txt Replaced
Fixes for api Call Streaming checks (one more fix on the way for minp/topk values for APIs)
Remove full API key debug statement in ‘chat()’
Wew, i'm an idiot.
Add Security fix notice
…or Linux/MacOS, but no code for them yet
Links + More Progress
Forgot to include the 'config.txt' changes...
Sorted out the RAG notes link dump. Still need to review/add the info to existing notes
Fixes + Links + Update to README
Update README.md
Update requirements.txt
Gradio now launches. 'Fix' was `pydantic==2.10.6`; Seems there's an issue with Gradio somewhere, and some update in the past few months caused this issue. yea. idk.
FIX FOR GRADIO NOT LAUNCHING
Lang config
…lation This commit introduces the ability for you to specify the desired language for audio and video transcriptions, preventing the system from forcing a translation to a default language (e.g., English). Key changes include: - Modified the Audio Ingestion Tab (Live Recording) to use the selected transcription language for both partial (live) and final transcriptions. `PartialTranscriptionThread` now accepts a language code. - Ensured the Audio Ingestion Tab (File/URL Processing) correctly passes the selected language code to the transcription backend. This was largely in place but verified. - Updated the core transcription logic in `Audio_Transcription_Lib.py` (`speech_to_text` function) to handle an "auto" language selection by passing `None` to the Whisper model, enabling its automatic language detection. - Verified that the Video Transcription Tab's existing infrastructure correctly propagates the selected language, including "auto-detect," to the transcription service. You can now select a specific language from the dropdown or choose "Auto-detect." The system will transcribe in the chosen language without an unwanted intermediate translation step.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
No description provided.