Skip to main content

Crate loqui_whisper

Crate loqui_whisper 

Source
Expand description

Whisper speech-to-text on whisper.cpp.

Decoding follows what open-speech asks of faster-whisper: beam search of width 5, temperature 0, an optional initial prompt, and a language that is detected unless given. Input is 16 kHz mono f32 (loqui_audio::decode_mono_16k produces it from any upload).

Weights are GGML files such as ggml-large-v3-turbo.bin from ggerganov/whisper.cpp; they are not bundled.

Structs§

Options
Segment
Transcription
Whisper

Enums§

Device
Where inference runs.
Error
Task