Multimodal Language Learning Aid

This app performs the following tasks:

1. Transcribes English speech using Wav2Vec2 (accepts text input as well).
2. Translates the English text to the target language using Helsinki-NLP models.
3. Provides speech:
   • For French, Spanish, Vietnamese, Indonesian, Turkish, Portuguese, and Korean: uses Facebook MMS TTS (VITS-based).
   • For Chinese and Japanese: uses myshell-ai MeloTTS models (work-in-progress).

Select your target language from the dropdown.