List your company

Speech Synthesis on Sound Effect (evaluation)

0.913M-STFTRNDVoC-shared
0.8641.194751.52551.85625Mar 9, 2026

Evaluation results

MethodLinks
RNDVoC-sharedPre-trained=LibriTTS2026.030.9134.5424.87
RNDVoC-nonsharedPre-trained=LibriTTS2026.030.9684.8434.821
BigVGAN‡Pre-trained=LibriTTS, Training Steps=5M steps2026.030.9984.8374.851
WaveFM‡Pre-trained=LibriTTS2026.031.0014.9834.851
Vocos‡Pre-trained=LibriTTS2026.031.115.7154.745
BigVGAN-base‡Pre-trained=LibriTTS, Training Steps=5M steps2026.031.1565.5774.716
PeriodWave‡Pre-trained=LibriTTS2026.031.2325.1974.595
HiFiGAN-V1Pre-trained=LibriTTS2026.031.4626.9714.291
AvocodoPre-trained=LibriTTS2026.031.4886.7954.426
iSTFTNet-V1Pre-trained=LibriTTS2026.031.547.3524.15
PriorGradPre-trained=LibriTTS2026.031.618.1064.289
FreGradPre-trained=LibriTTS2026.031.6698.3434.193
APNet2Pre-trained=LibriTTS2026.032.1388.3184.303