mirror of
https://github.com/hanzoai/engine.git
synced 2026-11-20 23:45:50 +00:00
29 lines
823 B
Rust
29 lines
823 B
Rust
//! Audio input processing with a multimodal model.
|
|
//!
|
|
//! Run with: `cargo run --release --example audio -p hanzo`
|
|
|
|
use anyhow::Result;
|
|
use hanzo::{AudioInput, MultimodalMessages, MultimodalModelBuilder, TextMessageRole};
|
|
|
|
#[tokio::main]
|
|
async fn main() -> Result<()> {
|
|
let model = MultimodalModelBuilder::new("../hf_models/gemma3n_e4b")
|
|
.with_logging()
|
|
.build()
|
|
.await?;
|
|
|
|
let audio_bytes = std::fs::read("sample_speech.wav")?;
|
|
let audio = AudioInput::from_bytes(&audio_bytes)?;
|
|
|
|
let messages = MultimodalMessages::new().add_audio_message(
|
|
TextMessageRole::User,
|
|
"What is being said?",
|
|
vec![audio],
|
|
);
|
|
|
|
let response = model.send_chat_request(messages).await?;
|
|
|
|
println!("{}", response.choices[0].message.content.as_ref().unwrap());
|
|
Ok(())
|
|
}
|