Spaces:

Cyberlace
/

api-swara-audio-analysis

Running on L4

App Files Files Community

api-swara-audio-analysis / app /services

69.1 kB

1 contributor

History: 11 commits

fariedalfarizi's picture

fix: add missing filler_ratio and update WITHOUT reference scoring ranges

30d0bb7 12 days ago

__init__.py

500 Bytes

Add profanity detection feature with 150+ Indonesian/English words 16 days ago
articulation.py

24.1 kB

fix: add missing filler_ratio and update WITHOUT reference scoring ranges 12 days ago
audio_processor.py

7.92 kB

feat: Unified articulation analysis with dual-mode (PER + Clarity) 12 days ago
filler_words.py

2.78 kB

feat: Add unified articulation system with dual-mode support 12 days ago
keywords.py

15.2 kB

Fix model caching - use HF_HOME for all models to prevent re-download on restart 12 days ago
speech_to_text.py

3.91 kB

Enable Whisper medium cache using /data persistent storage (HF Pro) 12 days ago
structure.py

9.15 kB

Fix structure detection - require keywords for opening/closing rules, prevent false positive from blind confidence trust 12 days ago
tempo.py

5.55 kB

Add profanity detection feature with 150+ Indonesian/English words 16 days ago