Merge pull request #66 from alibaba-damo-academy/dev_lzr

add infer_after_finetune in paraformer-large-vad-punc-model

egs_modelscope/asr_vad_punc/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/README.md

@@ -28,3 +28,19 @@ Or you can use the finetuned model for inference directly.
 ```python
     python infer.py
 ```
+
+### 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.pth`
+
+- 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.

egs_modelscope/asr_vad_punc/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer_after_finetune.py

@@ -0,0 +1,57 @@
+import json
+import os
+import shutil
+
+from modelscope.pipelines import pipeline
+from modelscope.utils.constant import Tasks
+
+from funasr.utils.compute_wer import compute_wer
+
+
+def modelscope_infer_after_finetune(params):
+    # prepare for decoding
+    if not os.path.exists(os.path.join(params["output_dir"], "punc")):
+        os.makedirs(os.path.join(params["output_dir"], "punc"))
+    if not os.path.exists(os.path.join(params["output_dir"], "vad")):
+        os.makedirs(os.path.join(params["output_dir"], "vad"))
+    pretrained_model_path = os.path.join(os.environ["HOME"], ".cache/modelscope/hub", params["modelscope_model_name"])
+    for file_name in params["required_files"]:
+        if file_name == "configuration.json":
+            with open(os.path.join(pretrained_model_path, file_name)) as f:
+                config_dict = json.load(f)
+                config_dict["model"]["am_model_name"] = params["decoding_model_name"]
+            with open(os.path.join(params["output_dir"], "configuration.json"), "w") as f:
+                json.dump(config_dict, f, indent=4, separators=(',', ': '))
+        else:
+            shutil.copy(os.path.join(pretrained_model_path, file_name),
+                        os.path.join(params["output_dir"], file_name))
+    decoding_path = os.path.join(params["output_dir"], "decode_results")
+    if os.path.exists(decoding_path):
+        shutil.rmtree(decoding_path)
+    os.mkdir(decoding_path)
+
+    # decoding
+    inference_pipeline = pipeline(
+        task=Tasks.auto_speech_recognition,
+        model=params["output_dir"],
+        output_dir=decoding_path,
+        batch_size=64
+    )
+    audio_in = os.path.join(params["data_dir"], "wav.scp")
+    inference_pipeline(audio_in=audio_in)
+
+    # computer CER if GT text is set
+    text_in = os.path.join(params["data_dir"], "text")
+    if text_in is not None:
+        text_proc_file = os.path.join(decoding_path, "1best_recog/token")
+        compute_wer(text_in, text_proc_file, os.path.join(decoding_path, "text.cer"))
+
+
+if __name__ == '__main__':
+    params = {}
+    params["modelscope_model_name"] = "damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
+    params["required_files"] = ["am.mvn", "decoding.yaml", "configuration.json", "punc/punc.pb", "punc/punc.yaml", "vad/vad.mvn", "vad/vad.pb", "vad/vad.yaml"]
+    params["output_dir"] = "./checkpoint"
+    params["data_dir"] = "./data/test"
+    params["decoding_model_name"] = "valid.acc.ave_10best.pth"
+    modelscope_infer_after_finetune(params)