whisper: use large-v3 model with Chinese language hint

src/main.rs

@@ -533,7 +533,8 @@ async fn transcribe_audio(whisper_url: &str, file_path: &Path) -> Result<String>
         .mime_str("audio/ogg")?;
     let form = reqwest::multipart::Form::new()
         .part("file", part)
-        .text("model", "base");
+        .text("model", "large-v3")
+        .text("language", "zh");
     let resp = client.post(&url).multipart(form).send().await?.error_for_status()?;
     let json: serde_json::Value = resp.json().await?;
     Ok(json["text"].as_str().unwrap_or("").to_string())