asr

type ASR interface {
	// Transcribe sends audio bytes to the ASR model and returns the transcribed text and segments.
	Transcribe(ctx context.Context, audioBytes []byte, fileName string) (*TranscriptionResult, error)

	GetModelName() string
	GetModelID() string
}

type Config struct {
	Source    types.ModelSource
	BaseURL   string
	ModelName string
	APIKey    string
	ModelID   string
	// Provider is the vendor id stored on the row; empty detects it from
	// BaseURL.
	Provider    string
	Spec        *types.ModelSpecOverride `json:"spec,omitempty"`
	ExtraConfig map[string]string
	// CustomHeaders 允许在调用远程 API 时附加自定义 HTTP 请求头（类似 OpenAI Python SDK 的 extra_headers）。
	CustomHeaders map[string]string
}

type Segment struct {
	Start float64 `json:"start"`
	End   float64 `json:"end"`
	Text  string  `json:"text"`
}

type TranscriptionResult struct {
	Text     string    `json:"text"`
	Segments []Segment `json:"segments,omitempty"`
	// Duration is the audio length in seconds when the vendor reports it,
	// which several do without segments; 0 when unknown.
	Duration float64 `json:"duration,omitempty"`
}