Module audio 

Audio Processing API Implementation

Provides access to HuggingFace’s audio processing models.

Features

• Automatic Speech Recognition (ASR): Convert speech to text
• Text-to-Speech (TTS): Generate speech from text
• Audio Classification: Classify audio into categories
• Audio-to-Audio: Transform audio (noise reduction, enhancement, etc.)

Usage

// Load audio file
let audio_data = fs::read( "speech.wav" )?;
let input = AudioInput::from_bytes( audio_data );

// Transcribe speech
let result = audio.transcribe( input, "openai/whisper-base" ).await?;
println!( "Transcription : {}", result );

Re-exports

pub use types::*;

Modules

asr

Automatic Speech Recognition ( ASR )

audio_to_audio

Audio-to-Audio Transformation

classification

Audio Classification

tts

Text-to-Speech (TTS)

types

Audio API Types

Structs

Audio

Audio API interface