mirror of
https://github.com/hanzoai/engine.git
synced 2026-11-21 02:00:12 +00:00
32 lines
869 B
Rust
32 lines
869 B
Rust
use anyhow::Result;
|
|
use hanzo::{AudioInput, MultimodalMessages, MultimodalModelBuilder, TextMessageRole};
|
|
|
|
#[tokio::main]
|
|
async fn main() -> Result<()> {
|
|
let model = MultimodalModelBuilder::new("mistralai/Voxtral-Mini-4B-Realtime-2602")
|
|
.with_logging()
|
|
.build()
|
|
.await?;
|
|
|
|
let audio_bytes = std::fs::read("sample_audio.wav")?;
|
|
let audio = AudioInput::from_bytes(&audio_bytes)?;
|
|
|
|
let messages = MultimodalMessages::new().add_multimodal_message(
|
|
TextMessageRole::User,
|
|
"Transcribe this audio.",
|
|
vec![],
|
|
vec![audio],
|
|
vec![],
|
|
);
|
|
|
|
let response = model.send_chat_request(messages).await?;
|
|
|
|
println!("{}", response.choices[0].message.content.as_ref().unwrap());
|
|
dbg!(
|
|
response.usage.avg_prompt_tok_per_sec,
|
|
response.usage.avg_compl_tok_per_sec
|
|
);
|
|
|
|
Ok(())
|
|
}
|