GitHub / yousefkotp / Egyptian-Arabic-ASR-and-Diarization
The official submission from Speech Squad team for the MTC-AIC 2 competition of 2024 where an ASR model is developed tailored for the Egyptian dialect, utilizing the FastConformer architecture. Our four-stage training pipeline achieved a Mean Levenshtein Distance score of 9.58 on the test set.
JSON API: http://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yousefkotp%2FEgyptian-Arabic-ASR-and-Diarization
PURL: pkg:github/yousefkotp/Egyptian-Arabic-ASR-and-Diarization
Stars: 7
Forks: 1
Open issues: 0
License: mit
Language: Jupyter Notebook
Size: 31 MB
Dependencies parsed at: Pending
Created at: about 1 year ago
Updated at: 6 months ago
Pushed at: 6 months ago
Last synced at: 6 months ago
Topics: aic, arabic-asr, arabic-nlp, arabic-speech-recognition, asr, deep-learning, egypitan-asr, egyptian, egyptian-dialect, egyptian-speech, mtc-aic, speech, speech-analysis, speech-processing, speech-recognition, speech-synthesis, tts