DiFlow-TTS: Compact and Low-Latency Zero-Shot Text-to-Speech with Discrete Flow Matching

[!NOTE] DiFlow-TTS is trained on 470 hours of the LibriTTS dataset, which consists of predominantly neutral speech. As a result, it may not perform well on prompts with strong emotional expression.

root/
└── ckpts/
    └── diflow-tts.ckpt