k2-fsa/OmniVoice
Text-to-Speech • Updated • 2.22M • 846
FSA/FST algorithms, differentiable, with PyTorch compatibility. Automatic speech recognition
asr with dolphin
Moonshine v2 base-en
Moonshine v2 base-ar
Moonshine v2 tiny ko
Moonshine v2 tiny-en
Moonshine v2 tiny-ja
Moonshine v2 base-uk
Generate speech audio from typed text instantly
Moonshine v2 base-es
Moonshine v2 base-zh
Transcribe spoken audio to text instantly
WebAssembly + Moonshine + VAD for ASR