Speech-to-text technology is becoming something we use daily, be it in texting functionality or visual voicemail on our cell phones, smart home devices, closed captioning on news channels, ...
Open source TTS models Kokoro, Orpheus, and Piper are tested on symbols, abbreviations, and prosody with CER and MOS results.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results