fae60a8120
Fix: Corrected shape handling for separated sources, extracting each source as a separate 1D array
2025-01-28 23:34:08 +05:30
9e7c01c19e
speech separation works, but ends up on either channels of same audio
2025-01-28 23:19:52 +05:30
88ebfb66f6
change model
2025-01-28 22:39:45 +05:30
2982aaaafd
add postprocessing package and create module for audio export
2025-01-28 20:33:57 +05:30
3914b2c5ba
remove unused parameter
2025-01-28 20:33:28 +05:30
7a7c27caa3
create ConvTasNet wrapper using asteroid
2025-01-28 20:20:48 +05:30
7295d4ff3d
enable cuda for classify_audio and demucs_wrapper
2025-01-25 17:38:27 +05:30
6a19dbed20
add code to display spectogram
2025-01-06 22:28:08 +05:30
08983d7e72
add code to generate spectogram array and plot_data
2025-01-06 22:11:49 +05:30
3b7bac94f7
create new package spectogram
2025-01-06 21:43:54 +05:30
8078d4ebd3
code cleanup
...
removed unused parameter from demucs_wrapper
2024-12-27 19:01:24 +00:00
6529572f4c
fix package initializations
2024-12-26 22:18:34 +05:30
cfd30185bd
add resample module in preprocessing package, refactor demucs_wrapper.py
2024-12-26 19:47:24 +05:30
96b4468138
using librosa to load the audio file
2024-12-26 16:50:29 +05:30
d0f6c8c77a
disable cuda for classify.py
2024-12-26 16:30:19 +05:30
1c71419537
use demucs with subprocess to separate music into bass, drums, vocals and other
2024-12-26 16:03:36 +05:30
e7c750483e
create separation package
2024-12-26 13:19:08 +05:30
e4abb070db
Implement audio classification function using YAMNet
...
- Create a function to load audio, resample, and classify using YAMNet
- Ensure compatibility with different audio formats and sample rates
- Normalize audio and classify it into one of 600 categories
2024-12-26 00:58:53 +05:30
cbebf7bd93
Remove unnecessary libraries and replace with librosa
...
- Removed unused imports for and
- Replaced resampling with for waveform handling
2024-12-26 00:49:10 +05:30
1ddbbadfc8
Integrate YAMNet for audio classification
...
- Added sample audio files: cafe_crowd_talk.wav, miaow_16k.wav, and speech_whistling2.wav
- Implemented YAMNet-based audio classification in classify.py
- Updated requirements.txt to include TensorFlow and dependencies for YAMNet
2024-12-26 00:41:23 +05:30
0ff6a12829
Implement audio normalization and trimming functions
...
- Normalize audio to the range [-1, 1]
- Trim silence from audio
- Add test cases for both functions
2024-12-24 20:59:41 +05:30
341d7fa11c
add preprocessing dir, add logging for module imports
2024-12-24 20:41:38 +05:30
919a798437
Initial setup: added src structure, input functionality, tests, and updated .gitignore
2024-12-24 17:52:27 +05:30
17f929e504
Setup input package with initial files
2024-12-24 17:07:43 +05:30
f9356ebb4e
add src dir
2024-12-24 16:33:27 +05:30
Joel Mathew Thomas