f5-tts_infer-cli --model "F5-TTS" --load_vocoder_from_local  --ref_audio "input0.wav" --ref_text "The content, subtitle or transcription of reference audio." --gen_text "Some text you want TTS model generate for you."
# f5-tts_infer-cli --model "F5-TTS" --load_vocoder_from_local  --ref_audio "input0.wav" --gen_text "Even when running the whisper-base, it's still very slow, compared to what it should be (on a 4090 GPU)"