Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Zero-shot Text-to-Speech on Chinese Speech Emotion Prompt
Loading...
0.0162
WER
IndexTTS2
0.013278
0.033206
0.053135
0.073064
Jan 6, 2026
WER
CER
DNSM
SSIM
NISQA
OVRL
SMOS
NMOS
SPMOS
Updated 4d ago
Evaluation Results
Method
Method
Links
WER
CER
DNSM
SSIM
NISQA
OVRL
SMOS
NMOS
SPMOS
IndexTTS2
2026.01
0.0162
0.0162
3.715
0.597
4.345
3.248
-
-
-
Segment-Aware Conditioning
2026.01
0.0273
0.0273
3.803
0.578
4.536
3.291
-
-
-
MaskGCT
2026.01
0.0814
0.0814
3.711
0.614
4.366
3.167
-
-
-
F5TTS
2026.01
0.09
0.09
3.386
0.598
4.286
3.204
-
-
-
Feedback
Search any
task
Search any
task