Tencent/WeKnora · error

transcribe audio: %w

Error message

transcribe audio: %w

What it means

Wraps a failure from asrModel.Transcribe when the loaded ASR model fails to transcribe the audio bytes. The model was found and loaded, but the transcription call itself failed (upstream provider error, unsupported codec, corrupted file, timeout, quota).

Source

Thrown at internal/application/service/temporary_document.go:381

	if options.ParserEngine == "" || options.ParserEngine == "auto" {
		if tenant, ok := ctx.Value(types.TenantInfoContextKey).(*types.Tenant); ok && tenant != nil {
			options.ParserEngine = tenant.ParserEngineConfig.ResolveChatParserEngine(ext)
		}
	}
	if _, ok := temporaryTextExtensions[ext]; ok && (options.ParserEngine == "" || options.ParserEngine == "auto") {
		return string(data), nil, map[string]string{"parser": "plain_text"}, nil
	}
	if docparser.IsAudioFormat(ext) {
		if options.ASRModelID == "" {
			return "", nil, nil, fmt.Errorf("audio transcription model is not configured")
		}
		asrModel, err := s.modelService.GetASRModel(ctx, options.ASRModelID)
		if err != nil {
			return "", nil, nil, fmt.Errorf("load ASR model: %w", err)
		}
		result, err := asrModel.Transcribe(ctx, data, document.FileName)
		if err != nil {
			return "", nil, nil, fmt.Errorf("transcribe audio: %w", err)
		}
		return result.Text, nil, map[string]string{"parser": "asr"}, nil
	}

	parserEngine := strings.TrimSpace(options.ParserEngine)
	if parserEngine == "auto" {
		parserEngine = ""
	}
	request := &types.ReadRequest{
		FileContent: data, FileName: document.FileName, FileType: strings.TrimPrefix(ext, "."),
		ParserEngine: parserEngine,
	}
	if tenant, ok := ctx.Value(types.TenantInfoContextKey).(*types.Tenant); ok && tenant != nil && tenant.ParserEngineConfig != nil {
		request.ParserEngineOverrides = tenant.ParserEngineConfig.ToOverridesMap()
	}
	deps := docparser.ReaderDeps{Overrides: request.ParserEngineOverrides, Remote: s.documentReader}
	if s.tenantService != nil {
		deps.WeKnoraCloudCredentials = s.tenantService.GetWeKnoraCloudCredentials

View on GitHub (pinned to 988cbb0330)

Solutions

1. Inspect the wrapped error to identify the ASR provider failure
2. Validate the audio file is a supported, uncorrupted format for the chosen ASR model
3. Check ASR provider credentials, quota, and network reachability
4. Retry the upload/transcription for transient provider errors

// pre-check: file extension supported by ASR model
if !supportedByASR(model, ext) { return errors.New("unsupported audio format for this ASR model") }

if err != nil {
    if strings.HasPrefix(err.Error(), "transcribe audio:") && isTransient(err) {
        // retry with backoff
    }
}

When it happens

Trigger: Process on an audio file where asrModel.Transcribe(ctx, data, document.FileName) returns an error — e.g. unsupported audio codec, file too large, ASR provider returns 4xx/5xx, or network failure to the ASR backend.

Common situations: Unsupported sample rate/codec sent to the ASR provider; ASR API key invalid or quota exhausted; audio file truncated/corrupt during upload; transient provider outage.

Related errors

• audio transcription model is not configured
• load ASR model: %w

AI-assisted analysis of Tencent/WeKnora@988cbb0330 (2026-09-02). Data as JSON: /api/errors/9bedfe45581a09a0. Report an issue: GitHub.