Open source TTS models Kokoro, Orpheus, and Piper are tested on symbols, abbreviations, and prosody with CER and MOS results.
Amazon.com Inc. researchers have developed a new text-to-speech model, Base TTS, that can pronounce words more naturally than earlier neural networks. TechCrunch reported the project late Wednesday.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results