diff options
| author | Paul Buetow <paul@buetow.org> | 2025-07-15 23:42:32 +0300 |
|---|---|---|
| committer | Paul Buetow <paul@buetow.org> | 2025-07-15 23:42:32 +0300 |
| commit | b105333c061ea165b3b79317415cbb8b9cfb7c75 (patch) | |
| tree | c2682cc156c372d85ab52d514df4316ceda9071d /cmd | |
| parent | 61529facc2c5321de9f0ab9123cb1de25bcab62c (diff) | |
feat: add English translations and detailed attribution files
- Automatic Bulgarian to English translation for all words
- Save translations to separate _translation.txt files
- Include translations in Anki CSV export
- Add detailed attribution files for audio and images:
- Audio: model, voice, speed, instructions, processed text
- Image: model, size, quality, style, full prompt used
- Expand image styles to 42 different options (including superhero comic, yoga, etc.)
- Improve image prompts to strongly avoid text generation
- Fix image overwrite issue - now overwrites existing files instead of failing
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
Diffstat (limited to 'cmd')
| -rw-r--r-- | cmd/totalrecall/main.go | 129 |
1 files changed, 124 insertions, 5 deletions
diff --git a/cmd/totalrecall/main.go b/cmd/totalrecall/main.go index 2a43d51..658301d 100644 --- a/cmd/totalrecall/main.go +++ b/cmd/totalrecall/main.go @@ -212,6 +212,22 @@ func runCommand(cmd *cobra.Command, args []string) error { } func processWord(word string) error { + // Translate the word first + fmt.Printf(" Translating to English...\n") + translation, err := translateWord(word) + if err != nil { + fmt.Printf(" Warning: Translation failed: %v\n", err) + translation = "" // Continue without translation + } else { + fmt.Printf(" Translation: %s\n", translation) + // Store translation for Anki export + wordTranslations[word] = translation + // Save translation to file + if err := saveTranslation(word, translation); err != nil { + fmt.Printf(" Warning: Failed to save translation: %v\n", err) + } + } + // Generate audio if !skipAudio { fmt.Printf(" Generating audio...\n") @@ -311,13 +327,25 @@ func generateAudioWithVoice(word, voice string) error { filename := sanitizeFilename(word) // Add voice name to filename if generating multiple voices + var outputFile string if allVoices { - outputFile := filepath.Join(outputDir, fmt.Sprintf("%s_%s.%s", filename, voice, audioFormat)) - return provider.GenerateAudio(ctx, word, outputFile) + outputFile = filepath.Join(outputDir, fmt.Sprintf("%s_%s.%s", filename, voice, audioFormat)) + } else { + outputFile = filepath.Join(outputDir, fmt.Sprintf("%s.%s", filename, audioFormat)) } - outputFile := filepath.Join(outputDir, fmt.Sprintf("%s.%s", filename, audioFormat)) - return provider.GenerateAudio(ctx, word, outputFile) + // Generate the audio + err = provider.GenerateAudio(ctx, word, outputFile) + if err != nil { + return err + } + + // Save audio attribution + if err := saveAudioAttribution(word, outputFile, providerConfig); err != nil { + fmt.Printf(" Warning: Failed to save audio attribution: %v\n", err) + } + + return nil } func downloadImages(word string) error { @@ -388,7 +416,7 @@ func downloadImages(word string) error { // Create downloader downloadOpts := &image.DownloadOptions{ OutputDir: outputDir, - OverwriteExisting: false, + OverwriteExisting: true, // Allow overwriting existing files CreateDir: true, FileNamePattern: "{word}_{index}", MaxSizeBytes: 5 * 1024 * 1024, // 5MB @@ -490,6 +518,13 @@ func generateAnkiCSV() error { return fmt.Errorf("failed to generate cards: %w", err) } + // Add translations to cards + for i := range gen.GetCards() { + if translation, ok := wordTranslations[gen.GetCards()[i].Bulgarian]; ok { + gen.GetCards()[i].Translation = translation + } + } + // Generate CSV if err := gen.GenerateCSV(); err != nil { return fmt.Errorf("failed to generate CSV: %w", err) @@ -593,6 +628,90 @@ func listAvailableModels() error { return nil } +func translateWord(word string) (string, error) { + // Use OpenAI to translate Bulgarian to English + apiKey := getOpenAIKey() + if apiKey == "" { + return "", fmt.Errorf("OpenAI API key not found") + } + + client := openai.NewClient(apiKey) + ctx := context.Background() + + req := openai.ChatCompletionRequest{ + Model: openai.GPT4oMini, + Messages: []openai.ChatCompletionMessage{ + { + Role: openai.ChatMessageRoleUser, + Content: fmt.Sprintf("Translate the Bulgarian word '%s' to English. Respond with only the English translation, nothing else.", word), + }, + }, + MaxTokens: 50, + Temperature: 0.3, + } + + resp, err := client.CreateChatCompletion(ctx, req) + if err != nil { + return "", fmt.Errorf("OpenAI API error: %w", err) + } + + if len(resp.Choices) == 0 { + return "", fmt.Errorf("no translation returned") + } + + translation := strings.TrimSpace(resp.Choices[0].Message.Content) + return translation, nil +} + +func saveTranslation(word, translation string) error { + // Save translation to a text file + filename := sanitizeFilename(word) + outputFile := filepath.Join(outputDir, fmt.Sprintf("%s_translation.txt", filename)) + + content := fmt.Sprintf("%s = %s\n", word, translation) + + if err := os.WriteFile(outputFile, []byte(content), 0644); err != nil { + return fmt.Errorf("failed to write translation file: %w", err) + } + + return nil +} + +// Global map to store translations for Anki export +var wordTranslations = make(map[string]string) + +func saveAudioAttribution(word, audioFile string, config *audio.Config) error { + // Create attribution text + attribution := fmt.Sprintf("Audio generated by OpenAI TTS\n\n") + attribution += fmt.Sprintf("Bulgarian word: %s\n", word) + attribution += fmt.Sprintf("Model: %s\n", config.OpenAIModel) + attribution += fmt.Sprintf("Voice: %s\n", config.OpenAIVoice) + attribution += fmt.Sprintf("Speed: %.2f\n", config.OpenAISpeed) + + if config.OpenAIInstruction != "" { + attribution += fmt.Sprintf("\nVoice instructions:\n%s\n", config.OpenAIInstruction) + } + + // Add preprocessing information + cleanedWord := strings.TrimSpace(word) + punctuationToRemove := []string{"!", "?", ".", ",", ";", ":", "\"", "'", "(", ")", "[", "]", "{", "}", "-", "—", "–"} + for _, punct := range punctuationToRemove { + cleanedWord = strings.ReplaceAll(cleanedWord, punct, "") + } + processedText := fmt.Sprintf("%s...", strings.TrimSpace(cleanedWord)) + attribution += fmt.Sprintf("\nProcessed text sent to TTS: %s\n", processedText) + + attribution += fmt.Sprintf("\nGenerated at: %s\n", time.Now().Format("2006-01-02 15:04:05")) + + // Save to file + attrPath := strings.TrimSuffix(audioFile, filepath.Ext(audioFile)) + "_attribution.txt" + if err := os.WriteFile(attrPath, []byte(attribution), 0644); err != nil { + return fmt.Errorf("failed to write audio attribution file: %w", err) + } + + return nil +} + func main() { if err := rootCmd.Execute(); err != nil { os.Exit(1) |
