From 9f9386d92f75be1bfa41938f86775a1be3ffa20b Mon Sep 17 00:00:00 2001 From: lzr265946 <lzr265946@alibaba-inc.com> Date: 星期五, 10 二月 2023 13:48:58 +0800 Subject: [PATCH] update paraformer-large RESULTS.md --- egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-aishell1-vocab8404-pytorch/RESULTS.md | 23 +++++++ egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/RESULTS.md | 75 +++++++++++++++++++++++++ egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-aishell2-vocab8404-pytorch/RESULTS.md | 25 ++++++++ 3 files changed, 123 insertions(+), 0 deletions(-) diff --git a/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-aishell1-vocab8404-pytorch/RESULTS.md b/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-aishell1-vocab8404-pytorch/RESULTS.md new file mode 100644 index 0000000..5eeae37 --- /dev/null +++ b/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-aishell1-vocab8404-pytorch/RESULTS.md @@ -0,0 +1,23 @@ +# Paraformer-Large +- Model link: <https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-aishell1-vocab8404-pytorch/summary> +- Model size: 220M + +# Environments +- date: `Fri Feb 10 13:34:24 CST 2023` +- python version: `3.7.12` +- FunASR version: `0.1.6` +- pytorch version: `pytorch 1.7.0` +- Git hash: `` +- Commit date: `` + +# Beachmark Results + +## AISHELL-1 +- Decode config: + - Decode without CTC + - Decode without LM + +| testset CER(%) | base model|finetune model | +|:--------------:|:---------:|:-------------:| +| dev | 1.75 |1.62 | +| test | 1.95 |1.78 | diff --git a/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-aishell2-vocab8404-pytorch/RESULTS.md b/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-aishell2-vocab8404-pytorch/RESULTS.md new file mode 100644 index 0000000..71d9fee --- /dev/null +++ b/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-aishell2-vocab8404-pytorch/RESULTS.md @@ -0,0 +1,25 @@ +# Paraformer-Large +- Model link: <https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-aishell2-vocab8404-pytorch/summary> +- Model size: 220M + +# Environments +- date: `Fri Feb 10 13:34:24 CST 2023` +- python version: `3.7.12` +- FunASR version: `0.1.6` +- pytorch version: `pytorch 1.7.0` +- Git hash: `` +- Commit date: `` + +# Beachmark Results + +## AISHELL-2 +- Decode config: + - Decode without CTC + - Decode without LM + +| testset | base model|finetune model| +|:------------:|:---------:|:------------:| +| dev_ios | 2.80 |2.60 | +| test_android | 3.13 |2.84 | +| test_ios | 2.85 |2.82 | +| test_mic | 3.06 |2.88 | diff --git a/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/RESULTS.md b/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/RESULTS.md new file mode 100644 index 0000000..ec95be3 --- /dev/null +++ b/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/RESULTS.md @@ -0,0 +1,75 @@ +# Paraformer-Large +- Model link: <https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary> +- Model size: 220M + +# Environments +- date: `Tue Nov 22 18:48:39 CST 2022` +- python version: `3.7.12` +- FunASR version: `0.1.0` +- pytorch version: `pytorch 1.7.0` +- Git hash: `` +- Commit date: `` + +# Beachmark Results + +## AISHELL-1 +- Decode config: + - Decode without CTC + - Decode without LM + +| testset | CER(%)| +|:---------:|:-----:| +| dev | 1.75 | +| test | 1.95 | + +## AISHELL-2 +- Decode config: + - Decode without CTC + - Decode without LM + +| testset | CER(%)| +|:------------:|:-----:| +| dev_ios | 2.80 | +| test_android | 3.13 | +| test_ios | 2.85 | +| test_mic | 3.06 | + +## Wenetspeech +- Decode config: + - Decode without CTC + - Decode without LM + +| testset | CER(%)| +|:---------:|:-----:| +| dev | 3.57 | +| test | 6.97 | +| test_net | 6.74 | + +## SpeechIO TIOBE +- Decode config 1: + - Decode without CTC + - Decode without LM + - With text norm +- Decode config 2: + - Decode without CTC + - Decode with Transformer-LM + - LM weight: 0.15 + - With text norm + +| testset | w/o LM | w/ LM | +|:------------------:|:----:|:----:| +|SPEECHIO_ASR_ZH00001| 0.49 | 0.35 | +|SPEECHIO_ASR_ZH00002| 3.23 | 2.86 | +|SPEECHIO_ASR_ZH00003| 1.13 | 0.80 | +|SPEECHIO_ASR_ZH00004| 1.33 | 1.10 | +|SPEECHIO_ASR_ZH00005| 1.41 | 1.18 | +|SPEECHIO_ASR_ZH00006| 5.25 | 4.85 | +|SPEECHIO_ASR_ZH00007| 5.51 | 4.97 | +|SPEECHIO_ASR_ZH00008| 3.69 | 3.18 | +|SPEECHIO_ASR_ZH00009| 3.02 | 2.78 | +|SPEECHIO_ASR_ZH000010| 3.35 | 2.99 | +|SPEECHIO_ASR_ZH000011| 1.54 | 1.25 | +|SPEECHIO_ASR_ZH000012| 2.06 | 1.68 | +|SPEECHIO_ASR_ZH000013| 2.57 | 2.25 | +|SPEECHIO_ASR_ZH000014| 3.86 | 3.08 | +|SPEECHIO_ASR_ZH000015| 3.34 | 2.67 | -- Gitblit v1.9.1