The original Arena's threshold is at 700 votes. But I am sure Kokoro will hold the position. The voice quality actually sounds close to ElevenLabs.
But StyleTTS usually is not very emotional. So it will fail where Edge TTS does. The phrases where the voice has to be sad or angry. For example Parler Expresso was overly jolly.
self.brag(): Kokoro finally got 300 votes in
Pendrokar/TTS-Spaces-Arena after
@Pendrokar
was kind enough to add it 3 weeks ago.
True, a sample from the original dataset would probably be the best. My attempt to try to fetch one from Emilia dataset was unsuccessful as HF dataset viewer can only show the German samples. Emilia's homepage has a ASMR-y example prompt given.
True about the narration style sample, but that still did not stop XTTS in surpassing F5. Both use the same sample.
TTS-AGI/TTS-Arena's button for downloading the DB data was available for a short while. The reason for removal must have been the unreviewed user submitted entries within the spokentext table. I've cleaned it up:
https://huggingface.co/datasets/Pendrokar/TTS_Arena_DB
Link to Spaces fork: https://huggingface.co/spaces/Pendrokar/TTS-Spaces-Arena
Link to Original Arena: https://huggingface.co/spaces/TTS-AGI/TTS-Arena
