Hugging Face's logo

Spaces:
Luigi
/
VoxSum
Sleeping

App Files Community
VoxSum / src

Commit History

Consolidate tests under tests/, add LLM default tests with opt-out flag, model selection, README update
913c94a

Luigi commited on

add gemma 270m for test use
59519b7

Luigi commited on

feat: Improve summarization quality and eliminate repetition
1e9d8a7

Luigi commited on

Implement multilingual summarization by only touching system prompts
110188a

Luigi commited on

Add speaker name detection feature
77e98bd

Luigi commited on

Fix llama-cpp-python blocking on HF Spaces due to excessive threads
0a56987

Luigi commited on

Fix Unicode encoding in export headers for Chinese filenames
81633d5

Luigi commited on

Fix filename sanitization for Chinese titles in export
72c7bbc

Luigi commited on

Apply zh-cn to zh-tw conversion on generated titles
33359da

Luigi commited on

Refine title generation prompt and parameters
ee32282

Luigi commited on

Implement document title generation and UI improvements
d8028fb

Luigi commited on

Convert summarization.py prompts and comments from French to English
299bf2b

Luigi commited on

Clean up legacy Streamlit implementation
228a065

Luigi commited on

Add langchain dependency for summarizer module
ca590d4

Luigi commited on

refactor: simplify and robustify summarization module
ae778ed

Luigi commited on

fix: handle long transcripts in summarization by chunking
88a0a34

Luigi commited on

status in result tab got more informative
030e33b

Luigi commited on

add non-tracked
9cd7aca

Luigi commited on

re-implement in FastAPI
ba4a241

Luigi commited on

Fix memory exhaustion on HF Spaces free tier by reducing n_ctx and implementing chunked summarization for long transcripts
09695c9

Luigi commited on

remove memory profiler from the proj.
2a2dcfd

Luigi commited on

fix: Reduce memory overhead from 2GB→10GB to 2GB→4GB for long audio files
de0b3d5

Luigi commited on

feat: CPU-friendly diarization with FAISS
6bf9bbb

Luigi commited on

get spk embedding model from hf models
7c59b7a

Luigi commited on

feat: Add inline editing and advanced export functionality
35d0046

Luigi commited on

Optimize speaker diarization performance for long audio files
e441a1a

Luigi commited on

Use writable model cache for diarization models; vendor improved_diarization in src\
fa3fe1c

Luigi commited on

Ignore __pycache__ and .pyc files
2fe01d1

Luigi commited on

Add vendored improved_diarization into src for Spaces importability
de5da7a

Luigi commited on

fix: unable to import improved_diarization.py on HF Spaces
9453a6f

Luigi commited on

feat: Add speaker diarization with CAM++ model integration
766564c

Luigi commited on

feat: Comprehensive UI optimizations for large audio files
55e88bd

Luigi commited on

security patches
6a822bc

Luigi commited on

default asr backend to sensevoice 2024
d744966

Luigi commited on

bugfix to permission err on model
d841847

Luigi commited on

add sensevoice small as 2nd ASR backend
624b770

Luigi commited on

remove Intelligent Transcript Sampling to preseve fidelity
4dde558

Luigi commited on

reduce large audio load time
1f718e5

Luigi commited on

code cleanning
b1ba3ee

Luigi commited on

work on llama.cpp huge loading time
395e2bc

Luigi commited on

Bugfix: Prevent Transcript Display from Disappearing During Summarization
9af0518

Luigi commited on

Update src/streamlit_app.py
010d5fd
verified

Luigi commited on

try re-enabling streaming transcript
b920ed0

Luigi commited on

fix duplication of summaries in ui
d7226ab

Luigi commited on

re-add summarization
a10fd4c

Luigi commited on

fix issue: player plays previous file after next audio is loaded
ceda09c

Luigi commited on

bugfix
4b51683

Luigi commited on

re-implement tab3 by gemini 2.5 pro
04b9905

Luigi commited on

add more debug msgs
254372f

Luigi commited on

add debug to chk current time
99c9fae

Luigi commited on