cjpais/Handy · error · anyhow::Error

Failed to load moonshine streaming model

Error message

Failed to load moonshine streaming model {}: {}

What it means

Thrown when StreamingModel::load from transcribe-rs fails to load the streaming Moonshine ONNX model at model_path (variant index 0, default quantization). The ONNX Runtime error is chained after the model_id and a "loading_failed" model-state event is emitted before the anyhow error is returned.

Solutions

1. Re-download the Moonshine streaming model from the model selector
2. Confirm the model directory actually contains the streaming-variant ONNX files and they are non-empty
3. Check the chained ONNX Runtime message for provider errors; try CPU accelerator
4. Fall back to the non-streaming Moonshine model while the streaming files are repaired

if !model_path.join("model.onnx").exists() {
    // streaming variant files missing: trigger re-download before load
    model_manager.ensure_downloaded(&model_id).await?;
}

if let Err(e) = manager.load_model(&model_id, None) {
    if e.to_string().contains("moonshine streaming") {
        // re-download then retry once; surface persistent failures to the user
    }
}

When it happens

Trigger: load_model hits EngineType::MoonshineStreaming and StreamingModel::load(&model_path, 0, &Quantization::default()) errors: streaming-variant files absent or corrupt under model_path, a base-variant directory used where the streaming layout is expected, or ONNX Runtime session creation fails.

Common situations: Corrupted/partial download of the streaming model; switching between Moonshine and Moonshine Streaming while files were half-written; version change in transcribe-rs expecting different streaming file names; missing onnxruntime provider libraries on Linux.

Related errors

• Failed to load moonshine model
• Failed to load canary model
• Failed to load cohere model
• Failed to load gigaam model
• Failed to load SenseVoice model

AI-assisted analysis of cjpais/Handy@ba10ce1943 (2026-08-17). Data as JSON: /api/errors/04096e15bd23b1de. Report an issue: GitHub.

Appendix: source

Thrown at src-tauri/src/managers/transcription.rs:670

                    MoonshineVariant::Base,
                    &Quantization::default(),
                )
                .map_err(|e| {
                    let error_msg = format!("Failed to load moonshine model {}: {}", model_id, e);
                    emit_loading_failed(&error_msg);
                    anyhow::anyhow!(error_msg)
                })?;
                LoadedEngine::Moonshine(engine)
            }
            EngineType::MoonshineStreaming => {
                let engine = StreamingModel::load(&model_path, 0, &Quantization::default())
                    .map_err(|e| {
                        let error_msg = format!(
                            "Failed to load moonshine streaming model {}: {}",
                            model_id, e
                        );
                        emit_loading_failed(&error_msg);
                        anyhow::anyhow!(error_msg)
                    })?;
                LoadedEngine::MoonshineStreaming(engine)
            }
            EngineType::SenseVoice => {
                let engine =
                    SenseVoiceModel::load(&model_path, &Quantization::Int8).map_err(|e| {
                        let error_msg =
                            format!("Failed to load SenseVoice model {}: {}", model_id, e);
                        emit_loading_failed(&error_msg);
                        anyhow::anyhow!(error_msg)
                    })?;
                LoadedEngine::SenseVoice(engine)
            }
            EngineType::GigaAM => {
                let engine = GigaAMModel::load(&model_path, &Quantization::Int8).map_err(|e| {
                    let error_msg = format!("Failed to load gigaam model {}: {}", model_id, e);
                    emit_loading_failed(&error_msg);
                    anyhow::anyhow!(error_msg)

View on GitHub (pinned to ba10ce1943)