Utilities managing the pretrained models created by Athena(v2.0)
git lfs clone git@git.lianjia.com:speech_tech/athena-group/athena-model-zoo.git| Language | Model Name | Training Data | Hours of Speech | Saved model | Chunk size | Error Rate |
|---|---|---|---|---|---|---|
| Chinese | Transformer-U2 | AISHELL Dataset | 178 h | asr/aishell/transformer-u2 | Full | 6.62% (CER) |
| Language | Model Name | Training Data | Saved model |
|---|---|---|---|
| Chinese | Fastspeech2 | data_baker | tts/data_baker/saved_model/ |
| Task | Model Name | Training Data | Input Segment | Frame Error Rate |
|---|---|---|---|---|
| VAD | DNN | Google Speech Commands Dataset V2 | 0.21s | 8.49% |
| VAD | MarbleNet | Google Speech Commands Dataset V2 | 0.63s | 2.50% |