# Leaderboard IO ## Configuration ### Data set: [Aishell1](https://www.openslr.org/33/): dev, test [Aishell2](https://www.aishelltech.com/aishell_2): dev_ios, test_ios, test_android, test_mic [WenetSpeech](https://github.com/wenet-e2e/WenetSpeech): dev, test_meeting, test_net ### Tools #### [Install Requirements](https://alibaba-damo-academy.github.io/FunASR/en/installation/installation.html#installation) Install ModelScope and FunASR from pip ```shell pip install -U modelscope funasr # For the users in China, you could install with the command: #pip install -U funasr -i https://mirror.sjtu.edu.cn/pypi/web/simple ``` Or install FunASR from source code ```shell git clone https://github.com/alibaba/FunASR.git && cd FunASR pip install -e ./ # For the users in China, you could install with the command: # pip install -e ./ -i https://mirror.sjtu.edu.cn/pypi/web/simple ``` #### Recipe ##### [Test CER](https://alibaba-damo-academy.github.io/FunASR/en/modelscope_pipeline/asr_pipeline.html#inference-with-multi-thread-cpus-or-multi-gpus) set the `model`, `data_dir` and `output_dir` in `infer.sh`. ```shell cd egs_modelscope/asr/TEMPLATE bash infer.sh ``` ## Benchmark CER ### Chinese Dataset
Model Offline/Online Aishell1 Aishell2 WenetSpeech
dev test dev_ios test_ios test_android test_mic dev test_meeting test_net
Paraformer-large Offline 1.76 1.94 2.79 2.84 3.08 3.03 3.43 7.01 6.66
Paraformer-large-long Offline 1.80 2.10 2.78 2.87 3.12 3.11 3.44 13.28 7.08
Paraformer-large-contextual Offline 1.76 2.02 2.73 2.85 2.98 2.95 3.42 7.16 6.72
Paraformer-large-online Online 2.37 3.34 4.04 3.86 4.38 4.21 4.55 10.64 7.78
Paraformer Offline 3.24 3.69 4.58 4.63 4.83 4.71 4.19 8.32 9.19
UniASR Online 3.34 3.99 4.62 4.52 4.77 4.73 4.51 10.63 9.70
UniASR-large Offline 2.93 3.48 3.95 3.87 4.11 4.11 4.16 10.09 8.69
Paraformer-aishell Offline 4.88 5.43 - - - - - - -
ParaformerBert-aishell Offline 6.14 7.01 - - - - - - -
Paraformer-aishell2 Offline - - 5.82 6.30 6.60 5.83 - - -
ParaformerBert-aishell2 Offline - - 4.95 5.45 5.59 5.83 - - -
### English Dataset