1
Automatic Speech Recognition
π
Transcribe speech to text
FSA/FST algorithms, differentiable, with PyTorch compatibility. Automatic speech recognition
Detect voice in spoken audio recordings
Generate speech from text with adjustable speed
Convert spoken words into text
Convert spoken words into text
Generate speech from text using Kaldi and WebAssembly
WebAssembly speech enhancement
Transcribe audio to text using ASR
Convert spoken words to text
Speaker diarization with Next-gen Kaldi and WebAssembly