Ben Nasedkin
025ff7fc55
Add support for Groq Whisper API as an alternative to OpenAI: - groq-transcription: Fast transcription using whisper-large-v3 or whisper-large-v3-turbo - groq-translation: Translation to English (whisper-large-v3 only) Features: - New transcription adapters for both Groq services - Config validation with provider-specific model restrictions - API key support via config file or GROQ_API_KEY environment variable - Updated interactive configuration wizard with provider selection - Comprehensive test coverage for all providers - Shared WAV conversion utility for audio preprocessing Breaking changes: None Backward compatibility: Existing OpenAI configurations continue to work unchanged
63 lines
1.5 KiB
Go
63 lines
1.5 KiB
Go
package transcriber
|
|
|
|
import (
|
|
"context"
|
|
"fmt"
|
|
|
|
"github.com/leonardotrapani/hyprvoice/internal/recording"
|
|
)
|
|
|
|
// Main transcriber interface
|
|
type Transcriber interface {
|
|
Start(ctx context.Context, frameCh <-chan recording.AudioFrame) (<-chan error, error)
|
|
Stop(ctx context.Context) error
|
|
GetFinalTranscription() (string, error)
|
|
}
|
|
|
|
// Adapter interface for different transcription backends
|
|
type TranscriptionAdapter interface {
|
|
Transcribe(ctx context.Context, audioData []byte) (string, error)
|
|
}
|
|
|
|
// Configuration for the transcriber
|
|
type Config struct {
|
|
Provider string
|
|
APIKey string
|
|
Language string
|
|
Model string
|
|
}
|
|
|
|
// NewTranscriber creates a new simple transcriber
|
|
func NewTranscriber(config Config) (Transcriber, error) {
|
|
// Create the appropriate adapter
|
|
var adapter TranscriptionAdapter
|
|
|
|
switch config.Provider {
|
|
case "openai":
|
|
if config.APIKey == "" {
|
|
return nil, fmt.Errorf("OpenAI API key required")
|
|
}
|
|
adapter = NewOpenAIAdapter(config)
|
|
|
|
case "groq-transcription":
|
|
if config.APIKey == "" {
|
|
return nil, fmt.Errorf("Groq API key required")
|
|
}
|
|
adapter = NewGroqTranscriptionAdapter(config)
|
|
|
|
case "groq-translation":
|
|
if config.APIKey == "" {
|
|
return nil, fmt.Errorf("Groq API key required")
|
|
}
|
|
adapter = NewGroqTranslationAdapter(config)
|
|
|
|
default:
|
|
return nil, fmt.Errorf("unsupported provider: %s", config.Provider)
|
|
}
|
|
|
|
// Create simple transcriber that collects all audio
|
|
transcriber := NewSimpleTranscriber(config, adapter)
|
|
|
|
return transcriber, nil
|
|
}
|