Dynamic Accent Flash: add Flash-DPO (CosyVoice3) as --version flash (default), diacritic front-end, Flash results, samples
e4ae2bb verified | {"step": 0, "val": {"acc": 0.0, "margin": 0.0}} | |
| {"step": 10, "of": 286, "loss": 0.9068, "acc": 0.625, "margin": 0.046, "gn": 57.21, "min": 0.1} | |
| {"step": 20, "of": 286, "loss": 0.9388, "acc": 0.5, "margin": -0.002, "gn": 66.55, "min": 0.1} | |
| {"step": 30, "of": 286, "loss": 0.9699, "acc": 0.375, "margin": -0.035, "gn": 61.96, "min": 0.2} | |
| {"step": 40, "of": 286, "loss": 0.938, "acc": 0.375, "margin": 0.011, "gn": 63.67, "min": 0.3} | |
| {"step": 50, "of": 286, "loss": 0.8633, "acc": 0.875, "margin": 0.15, "gn": 52.25, "min": 0.3} | |
| {"step": 60, "of": 286, "loss": 0.939, "acc": 0.625, "margin": 0.002, "gn": 63.83, "min": 0.4} | |
| {"step": 70, "of": 286, "loss": 0.8483, "acc": 0.75, "margin": 0.189, "gn": 69.48, "min": 0.4} | |
| {"step": 80, "of": 286, "loss": 1.0202, "acc": 0.375, "margin": -0.139, "gn": 80.15, "min": 0.5} | |
| {"step": 90, "of": 286, "loss": 0.8866, "acc": 0.625, "margin": 0.142, "gn": 59.47, "min": 0.5} | |
| {"step": 100, "of": 286, "loss": 0.8947, "acc": 0.625, "margin": 0.134, "gn": 60.78, "min": 0.6} | |
| {"step": 110, "of": 286, "loss": 0.9459, "acc": 0.5, "margin": 0.027, "gn": 66.75, "min": 0.6} | |
| {"step": 120, "of": 286, "loss": 1.0125, "acc": 0.375, "margin": -0.11, "gn": 65.48, "min": 0.7} | |
| {"step": 130, "of": 286, "loss": 0.8009, "acc": 0.75, "margin": 0.365, "gn": 50.92, "min": 0.8} | |
| {"step": 140, "of": 286, "loss": 0.8328, "acc": 0.75, "margin": 0.277, "gn": 60.21, "min": 0.8} | |
| {"epoch": 1, "step": 143, "val": {"acc": 0.6, "margin": 0.15548671048794252}} | |
| {"step": 150, "of": 286, "loss": 0.5242, "acc": 1.0, "margin": 1.345, "gn": 31.71, "min": 0.9} | |
| {"step": 160, "of": 286, "loss": 0.476, "acc": 1.0, "margin": 1.509, "gn": 28.95, "min": 0.9} | |
| {"step": 170, "of": 286, "loss": 0.5501, "acc": 1.0, "margin": 1.171, "gn": 29.98, "min": 1.0} | |
| {"step": 180, "of": 286, "loss": 0.474, "acc": 1.0, "margin": 1.492, "gn": 26.95, "min": 1.0} | |
| {"step": 190, "of": 286, "loss": 0.5711, "acc": 1.0, "margin": 1.032, "gn": 34.13, "min": 1.1} | |
| {"step": 200, "of": 286, "loss": 0.5283, "acc": 1.0, "margin": 1.181, "gn": 32.39, "min": 1.1} | |
| {"step": 210, "of": 286, "loss": 0.6212, "acc": 0.875, "margin": 0.86, "gn": 36.1, "min": 1.2} | |
| {"step": 220, "of": 286, "loss": 0.5229, "acc": 1.0, "margin": 1.227, "gn": 32.65, "min": 1.2} | |
| {"step": 230, "of": 286, "loss": 0.5555, "acc": 1.0, "margin": 1.367, "gn": 35.05, "min": 1.3} | |
| {"step": 240, "of": 286, "loss": 0.5312, "acc": 1.0, "margin": 1.314, "gn": 36.6, "min": 1.3} | |
| {"step": 250, "of": 286, "loss": 0.493, "acc": 1.0, "margin": 1.513, "gn": 28.32, "min": 1.3} | |
| {"step": 260, "of": 286, "loss": 0.5076, "acc": 1.0, "margin": 1.31, "gn": 25.17, "min": 1.4} | |
| {"step": 270, "of": 286, "loss": 0.434, "acc": 1.0, "margin": 1.739, "gn": 23.64, "min": 1.4} | |
| {"step": 280, "of": 286, "loss": 0.4263, "acc": 1.0, "margin": 1.907, "gn": 24.99, "min": 1.5} | |
| {"epoch": 2, "step": 286, "val": {"acc": 0.65, "margin": 0.17853533582141}} | |