facodec
https://github.com/lifeiteng/naturalspeech3_facodecBitrate: 4.8 kbps
Model size: 29 M params
| Language | Mel L1 | PESQ | STOI | Speaker sim |
|---|---|---|---|---|
| All languages | 0.45 ± 0.06 | 2.09 ± 0.52 | 0.87 ± 0.08 | 0.79 ± 0.11 |
| Arabic | 0.46 ± 0.07 | 2.08 ± 0.52 | 0.86 ± 0.08 | 0.77 ± 0.13 |
| Armenian | 0.45 ± 0.07 | 2.03 ± 0.51 | 0.85 ± 0.10 | 0.75 ± 0.16 |
| Azerbaijani | 0.44 ± 0.05 | 2.15 ± 0.51 | 0.87 ± 0.06 | 0.77 ± 0.11 |
| Chinese | 0.50 ± 0.10 | 2.05 ± 0.57 | 0.88 ± 0.08 | 0.79 ± 0.08 |
| Croatian | 0.43 ± 0.04 | 2.37 ± 0.78 | 0.88 ± 0.06 | 0.82 ± 0.06 |
| Danish | 0.45 ± 0.06 | 2.09 ± 0.55 | 0.86 ± 0.07 | 0.79 ± 0.10 |
| Dutch | 0.44 ± 0.05 | 1.97 ± 0.48 | 0.86 ± 0.07 | 0.79 ± 0.10 |
| English | 0.45 ± 0.06 | 2.13 ± 0.62 | 0.86 ± 0.09 | 0.79 ± 0.12 |
| Estonian | 0.44 ± 0.06 | 2.16 ± 0.53 | 0.87 ± 0.08 | 0.79 ± 0.10 |
| Finnish | 0.45 ± 0.06 | 2.14 ± 0.54 | 0.86 ± 0.08 | 0.81 ± 0.09 |
| French | 0.44 ± 0.06 | 2.10 ± 0.39 | 0.89 ± 0.06 | 0.81 ± 0.07 |
| German | 0.44 ± 0.04 | 2.04 ± 0.44 | 0.88 ± 0.05 | 0.83 ± 0.07 |
| Greek | 0.54 ± 0.11 | 1.39 ± 0.39 | 0.76 ± 0.11 | 0.59 ± 0.19 |
| Hungarian | 0.41 ± 0.03 | 2.31 ± 0.49 | 0.89 ± 0.04 | 0.78 ± 0.07 |
| Icelandic | 0.44 ± 0.06 | 2.18 ± 0.48 | 0.88 ± 0.06 | 0.80 ± 0.12 |
| Italian | 0.45 ± 0.05 | 2.07 ± 0.42 | 0.87 ± 0.07 | 0.80 ± 0.09 |
| Japanese | 0.46 ± 0.07 | 1.92 ± 0.59 | 0.84 ± 0.10 | 0.75 ± 0.12 |
| Latvian | 0.42 ± 0.05 | 2.24 ± 0.53 | 0.89 ± 0.06 | 0.81 ± 0.09 |
| Lithuanian | 0.44 ± 0.05 | 1.88 ± 0.43 | 0.84 ± 0.09 | 0.75 ± 0.11 |
| Macedonian | 0.43 ± 0.06 | 2.12 ± 0.33 | 0.81 ± 0.21 | 0.75 ± 0.14 |
| Norwegian | 0.44 ± 0.06 | 2.23 ± 0.44 | 0.87 ± 0.07 | 0.81 ± 0.09 |
| Norwegian Nynorsk | 0.46 ± 0.13 | 2.46 ± 1.11 | 0.89 ± 0.12 | 0.80 ± 0.16 |
| Persian | 0.47 ± 0.08 | 2.12 ± 0.56 | 0.86 ± 0.11 | 0.77 ± 0.13 |
| Polish | 0.62 ± 0.10 | 1.16 ± 0.15 | 0.60 ± 0.24 | 0.32 ± 0.35 |
| Portuguese | 0.63 ± 0.00 | 1.58 ± 0.00 | 0.77 ± 0.00 | 0.72 ± 0.00 |
| Russian | 0.46 ± 0.06 | 1.92 ± 0.54 | 0.86 ± 0.06 | 0.81 ± 0.06 |
| Serbian | 0.47 ± 0.08 | 1.93 ± 0.54 | 0.84 ± 0.08 | 0.77 ± 0.15 |
| Slovenian | 0.46 ± 0.06 | 2.13 ± 0.48 | 0.87 ± 0.04 | 0.77 ± 0.10 |
| Spanish | 0.47 ± 0.07 | 1.95 ± 0.42 | 0.86 ± 0.07 | 0.80 ± 0.11 |
| Swedish | 0.43 ± 0.05 | 2.23 ± 0.52 | 0.88 ± 0.06 | 0.84 ± 0.08 |
| Turkish | 0.45 ± 0.06 | 2.10 ± 0.57 | 0.87 ± 0.07 | 0.79 ± 0.10 |
| Ukrainian | 0.46 ± 0.04 | 1.93 ± 0.49 | 0.84 ± 0.07 | 0.75 ± 0.14 |
| Urdu | 0.47 ± 0.08 | 2.06 ± 0.50 | 0.87 ± 0.09 | 0.79 ± 0.09 |