Skip to main content

AudioToText

zai_rs::model::traits

Trait AudioToText 

Source 
pub trait AudioToText: ModelName + AudioToText { }
Expand description

Indicates that an official model supports speech recognition.

This trait is sealed because the ASR request schema is frozen to the documented model ids. Downstream crates cannot opt arbitrary model names into that schema.

ⓘ
use zai_rs::model::traits::{AudioToText, ModelName};

#[derive(serde::Serialize)]
struct UnofficialAsr;

impl From<UnofficialAsr> for String {
    fn from(_: UnofficialAsr) -> Self {
        "unofficial-asr".to_owned()
    }
}

impl ModelName for UnofficialAsr {
    const NAME: &'static str = "unofficial-asr";
}
impl AudioToText for UnofficialAsr {}

Dyn Compatibility§

This trait is not dyn compatible.

In older versions of Rust, dyn compatibility was called "object safety".

Implementors§