Speech Recognition and Audio Processing
21 repos
Automatic speech recognition (ASR) systems and audio processing tools, centered around OpenAI's Whisper model and its variants. These repositories provide implementations, optimizations, and language-specific adaptations of speech-to-text technology, enabling developers to build voice input capabilities into applications across different platforms and use cases.
whisper ·1,419
automatic-speech-recognition ·1,419
safetensors ·1,181
transformers ·1,181
endpoints_compatible ·1,146
eval-results ·891
en ·870
de ·688
audio ·249
hf-asr-leaderboard ·249
