List your company

Text-to-Speech on LibriTTS zero-shot

4.3026UTMOSPeriodWave-Turbo-L
3.9600244.0489624.13794.226838Aug 14, 2024Aug 15, 2024

Evaluation results

MethodLinks
PeriodWave-Turbo-LSampling Steps=4, ODE Solver=Euler2024.084.30264.320.51.490.5790.835——
PeriodWave-Turbo-BSampling Steps=4, ODE Solver=Euler2024.084.29324.330.521.520.5760.835——
PeriodWave-Turbo-SSampling Steps=4, ODE Solver=Euler2024.084.27164.340.641.640.5750.835——
PeriodWave-L + FreeUSampling Steps=16, ODE Solver=Midpoint, FreeU=true2024.084.26434.290.571.60.560.833——
PeriodWavesampling steps=16, zero-shot=true, FreeU=true2024.084.2621———————
PeriodWave-B + FreeUSampling Steps=16, ODE Solver=Midpoint, FreeU=true2024.084.26214.310.591.650.5560.835——
PeriodWave-LSampling Steps=16, ODE Solver=Midpoint2024.084.24644.270.591.650.5570.821——
PeriodWavesampling steps=16, zero-shot=true2024.084.2209———————
PeriodWave-BSampling Steps=16, ODE Solver=Midpoint2024.084.22094.30.591.650.5530.837——
BigVGANzero-shot=true, training_steps=5M2024.084.0424———————
BigVGAN2024.084.04244.280.591.60.5760.836——
BigVGAN-v22024.083.98944.240.541.530.5790.835——
BigVSANzero-shot=true, training_steps=10M2024.083.9732———————
BigVSAN2024.083.97324.260.581.630.5730.835——
CosyVoice 2Source ZS-TTS Model=CV2, Training Data=Real 10% + Synth 90%, DC=✓, OS=✓2026.03———————61.8
Fish-SpeechSource ZS-TTS Model=FS, Training Data=Real 10% + Synth 90%, DC=-, OS=-2026.03——————3.86—
Fish-SpeechSource ZS-TTS Model=FS, Training Data=Real 10% + Synth 90%, DC=✓, OS=✓2026.03——————3.9270.8
Ground Truth (Recordings)Training Data=-, DC=-, OS=-2026.03——————4.31—
Real-OnlyTraining Data=Real 10%, DC=-, OS=-2026.03——————3.58—
Real-OnlyTraining Data=Real 100%, DC=-, OS=-2026.03——————3.67—