Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/kavayk29/speech-recognition-using-tdnn-and-data-augmentation
Developed a speech recognition system using TDNN, preprocessing audio, extracting MFCC features, and training the model. Fine-tuning with augmented data (19,000 rows) improved accuracy from 9% to 80% training and 40% validation. Data augmentation proved crucial for enhancing model performance and generalization. Still working to increase the acc.
https://github.com/kavayk29/speech-recognition-using-tdnn-and-data-augmentation
deep-learning keras-tensorflow numpy os pandas tdnn tensorflow
Last synced: 15 days ago
JSON representation
Developed a speech recognition system using TDNN, preprocessing audio, extracting MFCC features, and training the model. Fine-tuning with augmented data (19,000 rows) improved accuracy from 9% to 80% training and 40% validation. Data augmentation proved crucial for enhancing model performance and generalization. Still working to increase the acc.
- Host: GitHub
- URL: https://github.com/kavayk29/speech-recognition-using-tdnn-and-data-augmentation
- Owner: Kavayk29
- Created: 2024-09-12T17:43:55.000Z (2 months ago)
- Default Branch: main
- Last Pushed: 2024-09-14T05:31:11.000Z (2 months ago)
- Last Synced: 2024-10-31T13:04:37.841Z (15 days ago)
- Topics: deep-learning, keras-tensorflow, numpy, os, pandas, tdnn, tensorflow
- Language: Jupyter Notebook
- Homepage:
- Size: 1.01 GB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md