Model
Tacotron2
Google提出的端到端TTS语音合成模型，引入序列到序列（Seq2Seq）架构，将文字到声学特征的转换与波形生成整合，显著提升合成速度与自然度
Timeline (last 90 days)
Oct 11
Tacotron2 is a two-stage pipeline that first converts text into a mel spectrogram and then synthesizes the waveform through a vocoder such as WaveGlow or HiFi-GAN.
Unverified50%
Oct 11
VITS is an end-to-end single-stage model that is typically 2–3 times faster than Tacotron2 on equivalent hardware and achieves higher quality.
Unverified50%
All Facts (2)
Unverified
Tacotron2 is a two-stage pipeline that first converts text into a mel spectrogram and then synthesizes the waveform through a vocoder such as WaveGlow or HiFi-GAN.
50%UnverifiedVITS is an end-to-end single-stage model that is typically 2–3 times faster than Tacotron2 on equivalent hardware and achieves higher quality.
50%