c93f4e94ae
- Implemented a new function to check ASR model connectivity via the /v1/audio/transcriptions endpoint. - Updated ModelEditorDialog.vue to integrate ASR model checks and adjust UI elements accordingly. - Enhanced localization files to reflect changes in ASR terminology and descriptions. - Added ASR configuration options to the knowledge base and updated related migration scripts. - Refactored model handling to support ASR as a distinct model type in the application.
33 lines
879 B
Go
33 lines
879 B
Go
package asr
|
|
|
|
import (
|
|
"context"
|
|
|
|
"github.com/Tencent/WeKnora/internal/types"
|
|
)
|
|
|
|
// ASR defines the interface for Automatic Speech Recognition model operations.
|
|
type ASR interface {
|
|
// Transcribe sends audio bytes to the ASR model and returns the transcribed text.
|
|
Transcribe(ctx context.Context, audioBytes []byte, fileName string) (string, error)
|
|
|
|
GetModelName() string
|
|
GetModelID() string
|
|
}
|
|
|
|
// Config holds the configuration needed to create an ASR instance.
|
|
type Config struct {
|
|
Source types.ModelSource
|
|
BaseURL string
|
|
ModelName string
|
|
APIKey string
|
|
ModelID string
|
|
Language string // optional: specify language for transcription
|
|
}
|
|
|
|
// NewASR creates an ASR instance based on the provided configuration.
|
|
// All ASR vendors use the OpenAI-compatible /v1/audio/transcriptions API.
|
|
func NewASR(config *Config) (ASR, error) {
|
|
return NewOpenAIASR(config)
|
|
}
|