mirror of
https://github.com/sipeed/picoclaw.git
synced 2026-06-12 18:08:54 +00:00
RussellLuo
8ad4b9b497
- Add `AudioModelTranscriber` for model-based audio transcription via LLM providers - Support selecting a transcription model with `voice.model_name` in config - Keep Groq transcription as a fallback and move it into dedicated files with focused tests - Serialize `data:audio/...` media as input_audio for OpenAI-compatible providers - Improve transcription logging by rendering error fields as strings - Add coverage for transcriber detection, audio-model behavior, provider audio serialization, and Groq transcription Fixes #1890.
85 lines
2.3 KiB
Go
85 lines
2.3 KiB
Go
package voice
|
|
|
|
import (
|
|
"context"
|
|
"encoding/json"
|
|
"net/http"
|
|
"net/http/httptest"
|
|
"os"
|
|
"path/filepath"
|
|
"testing"
|
|
)
|
|
|
|
var _ Transcriber = (*GroqTranscriber)(nil)
|
|
|
|
func TestGroqTranscriberName(t *testing.T) {
|
|
tr := NewGroqTranscriber("sk-test")
|
|
if got := tr.Name(); got != "groq" {
|
|
t.Errorf("Name() = %q, want %q", got, "groq")
|
|
}
|
|
}
|
|
|
|
func TestGroqTranscribe(t *testing.T) {
|
|
// Write a minimal fake audio file so the transcriber can open and send it.
|
|
tmpDir := t.TempDir()
|
|
audioPath := filepath.Join(tmpDir, "clip.ogg")
|
|
if err := os.WriteFile(audioPath, []byte("fake-audio-data"), 0o644); err != nil {
|
|
t.Fatalf("failed to write fake audio file: %v", err)
|
|
}
|
|
|
|
t.Run("success", func(t *testing.T) {
|
|
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
|
if r.URL.Path != "/audio/transcriptions" {
|
|
t.Errorf("unexpected path: %s", r.URL.Path)
|
|
}
|
|
if r.Header.Get("Authorization") != "Bearer sk-test" {
|
|
t.Errorf("unexpected Authorization header: %s", r.Header.Get("Authorization"))
|
|
}
|
|
w.Header().Set("Content-Type", "application/json")
|
|
_ = json.NewEncoder(w).Encode(TranscriptionResponse{
|
|
Text: "hello world",
|
|
Language: "en",
|
|
Duration: 1.5,
|
|
})
|
|
}))
|
|
defer srv.Close()
|
|
|
|
tr := NewGroqTranscriber("sk-test")
|
|
tr.apiBase = srv.URL
|
|
|
|
resp, err := tr.Transcribe(context.Background(), audioPath)
|
|
if err != nil {
|
|
t.Fatalf("Transcribe() error: %v", err)
|
|
}
|
|
if resp.Text != "hello world" {
|
|
t.Errorf("Text = %q, want %q", resp.Text, "hello world")
|
|
}
|
|
if resp.Language != "en" {
|
|
t.Errorf("Language = %q, want %q", resp.Language, "en")
|
|
}
|
|
})
|
|
|
|
t.Run("api error", func(t *testing.T) {
|
|
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
|
http.Error(w, `{"error":"invalid_api_key"}`, http.StatusUnauthorized)
|
|
}))
|
|
defer srv.Close()
|
|
|
|
tr := NewGroqTranscriber("sk-bad")
|
|
tr.apiBase = srv.URL
|
|
|
|
_, err := tr.Transcribe(context.Background(), audioPath)
|
|
if err == nil {
|
|
t.Fatal("expected error for non-200 response, got nil")
|
|
}
|
|
})
|
|
|
|
t.Run("missing file", func(t *testing.T) {
|
|
tr := NewGroqTranscriber("sk-test")
|
|
_, err := tr.Transcribe(context.Background(), filepath.Join(tmpDir, "nonexistent.ogg"))
|
|
if err == nil {
|
|
t.Fatal("expected error for missing file, got nil")
|
|
}
|
|
})
|
|
}
|