From 6427c834dfd97b1f05c6659cdc7ccf010bf82fe1 Mon Sep 17 00:00:00 2001
From: 嘉渊 <wangjiaming.wjm@alibaba-inc.com>
Date: 星期一, 24 四月 2023 19:50:07 +0800
Subject: [PATCH] update
---
egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/README.md | 34 +++++++++++++++++++++++++++++-----
1 files changed, 29 insertions(+), 5 deletions(-)
diff --git a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/README.md b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/README.md
index c68a8cd..eff933e 100644
--- a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/README.md
+++ b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/README.md
@@ -1,13 +1,14 @@
# ModelScope Model
-## How to finetune and infer using a pretrained Paraformer-large Model
+## How to finetune and infer using a pretrained UniASR Model
### Finetune
- Modify finetune training related parameters in `finetune.py`
- <strong>output_dir:</strong> # result dir
- - <strong>data_dir:</strong> # the dataset dir needs to include files: train/wav.scp, train/text; validation/wav.scp, validation/text.
- - <strong>batch_bins:</strong> # batch size
+ - <strong>data_dir:</strong> # the dataset dir needs to include files: `train/wav.scp`, `train/text`; `validation/wav.scp`, `validation/text`
+ - <strong>dataset_type:</strong> # for dataset larger than 1000 hours, set as `large`, otherwise set as `small`
+ - <strong>batch_bins:</strong> # batch size. For dataset_type is `small`, `batch_bins` indicates the feature frames. For dataset_type is `large`, `batch_bins` indicates the duration in ms
- <strong>max_epoch:</strong> # number of training epoch
- <strong>lr:</strong> # learning rate
@@ -21,10 +22,33 @@
Or you can use the finetuned model for inference directly.
- Setting parameters in `infer.py`
- - <strong>audio_in:</strong> # support wav, url, bytes, and parsed audio format.
- - <strong>output_dir:</strong> # If the input format is wav.scp, it needs to be set.
+ - <strong>data_dir:</strong> # the dataset dir needs to include `test/wav.scp`. If `test/text` is also exists, CER will be computed
+ - <strong>output_dir:</strong> # result dir
+ - <strong>ngpu:</strong> # the number of GPUs for decoding
+ - <strong>njob:</strong> # the number of jobs for each GPU
- Then you can run the pipeline to infer with:
```python
python infer.py
```
+
+- Results
+
+The decoding results can be found in `$output_dir/1best_recog/text.cer`, which includes recognition results of each sample and the CER metric of the whole test set.
+
+### Inference using local finetuned model
+
+- Modify inference related parameters in `infer_after_finetune.py`
+ - <strong>output_dir:</strong> # result dir
+ - <strong>data_dir:</strong> # the dataset dir needs to include `test/wav.scp`. If `test/text` is also exists, CER will be computed
+ - <strong>decoding_model_name:</strong> # set the checkpoint name for decoding, e.g., `valid.cer_ctc.ave
+ .pb`
+
+- Then you can run the pipeline to finetune with:
+```python
+ python infer_after_finetune.py
+```
+
+- Results
+
+The decoding results can be found in `$output_dir/decoding_results/text.cer`, which includes recognition results of each sample and the CER metric of the whole test set.
--
Gitblit v1.9.1