update egs_modelscope recipe

egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-aishell1-vocab8404-pytorch/infer.py

@@ -8,9 +8,14 @@ from modelscope.utils.constant import Tasks
 from funasr.utils.compute_wer import compute_wer
 
 
-def modelscope_infer_core(output_dir, split_dir, njob, idx):
+def modelscope_infer_core(output_dir, split_dir, njob, idx, batch_size, ngpu, model):
     output_dir_job = os.path.join(output_dir, "output.{}".format(idx))
-    gpu_id = (int(idx) - 1) // njob
+    if ngpu > 0:
+        use_gpu = 1
+        gpu_id = int(idx) - 1
+    else:
+        use_gpu = 0
+        gpu_id = -1
     if "CUDA_VISIBLE_DEVICES" in os.environ.keys():
         gpu_list = os.environ['CUDA_VISIBLE_DEVICES'].split(",")
         os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_list[gpu_id])
@@ -18,9 +23,10 @@ def modelscope_infer_core(output_dir, split_dir, njob, idx):
         os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_id)
     inference_pipline = pipeline(
         task=Tasks.auto_speech_recognition,
-        model="damo/speech_paraformer-large_asr_nat-zh-cn-16k-aishell1-vocab8404-pytorch",
+        model=model,
         output_dir=output_dir_job,
-        batch_size=64
+        batch_size=batch_size,
+        ngpu=use_gpu,
     )
     audio_in = os.path.join(split_dir, "wav.{}.scp".format(idx))
     inference_pipline(audio_in=audio_in)
@@ -30,13 +36,18 @@ def modelscope_infer(params):
     # prepare for multi-GPU decoding
     ngpu = params["ngpu"]
     njob = params["njob"]
+    batch_size = params["batch_size"]
     output_dir = params["output_dir"]
+    model = params["model"]
     if os.path.exists(output_dir):
         shutil.rmtree(output_dir)
     os.mkdir(output_dir)
     split_dir = os.path.join(output_dir, "split")
     os.mkdir(split_dir)
-    nj = ngpu * njob
+    if ngpu > 0:
+        nj = ngpu
+    elif ngpu == 0:
+        nj = njob
     wav_scp_file = os.path.join(params["data_dir"], "wav.scp")
     with open(wav_scp_file) as f:
         lines = f.readlines()
@@ -56,7 +67,7 @@ def modelscope_infer(params):
     p = Pool(nj)
     for i in range(nj):
         p.apply_async(modelscope_infer_core,
-                      args=(output_dir, split_dir, njob, str(i + 1)))
+                      args=(output_dir, split_dir, njob, str(i + 1), batch_size, ngpu, model))
     p.close()
     p.join()
 
@@ -81,8 +92,10 @@ def modelscope_infer(params):
 
 if __name__ == "__main__":
     params = {}
+    params["model"] = "damo/speech_paraformer-large_asr_nat-zh-cn-16k-aishell1-vocab8404-pytorch"
     params["data_dir"] = "./data/test"
     params["output_dir"] = "./results"
-    params["ngpu"] = 1
-    params["njob"] = 1
-    modelscope_infer(params)
+    params["ngpu"] = 1 # if ngpu > 0, will use gpu decoding
+    params["njob"] = 1 # if ngpu = 0, will use cpu decoding
+    params["batch_size"] = 64
+    modelscope_infer(params)

egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-aishell1-vocab8404-pytorch/infer_after_finetune.py

@@ -4,23 +4,18 @@ import shutil
 
 from modelscope.pipelines import pipeline
 from modelscope.utils.constant import Tasks
+from modelscope.hub.snapshot_download import snapshot_download
 
 from funasr.utils.compute_wer import compute_wer
 
-
 def modelscope_infer_after_finetune(params):
     # prepare for decoding
-    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))
+
+    try:
+        pretrained_model_path = snapshot_download(params["modelscope_model_name"], cache_dir=params["output_dir"])
+    except BaseException:
+        raise BaseException(f"Please download pretrain model from ModelScope firstly.")
+    shutil.copy(os.path.join(params["output_dir"], params["decoding_model_name"]), os.path.join(pretrained_model_path, "model.pb"))
     decoding_path = os.path.join(params["output_dir"], "decode_results")
     if os.path.exists(decoding_path):
         shutil.rmtree(decoding_path)
@@ -29,9 +24,9 @@ def modelscope_infer_after_finetune(params):
     # decoding
     inference_pipeline = pipeline(
         task=Tasks.auto_speech_recognition,
-        model=params["output_dir"],
+        model=pretrained_model_path,
         output_dir=decoding_path,
-        batch_size=64
+        batch_size=params["batch_size"]
     )
     audio_in = os.path.join(params["data_dir"], "wav.scp")
     inference_pipeline(audio_in=audio_in)
@@ -46,8 +41,8 @@ def modelscope_infer_after_finetune(params):
 if __name__ == '__main__':
     params = {}
     params["modelscope_model_name"] = "damo/speech_paraformer-large_asr_nat-zh-cn-16k-aishell1-vocab8404-pytorch"
-    params["required_files"] = ["am.mvn", "decoding.yaml", "configuration.json"]
     params["output_dir"] = "./checkpoint"
     params["data_dir"] = "./data/test"
     params["decoding_model_name"] = "valid.acc.ave_10best.pb"
-    modelscope_infer_after_finetune(params)
+    params["batch_size"] = 64
+    modelscope_infer_after_finetune(params)

egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-aishell2-vocab8404-pytorch/infer.py

@@ -8,9 +8,14 @@ from modelscope.utils.constant import Tasks
 from funasr.utils.compute_wer import compute_wer
 
 
-def modelscope_infer_core(output_dir, split_dir, njob, idx):
+def modelscope_infer_core(output_dir, split_dir, njob, idx, batch_size, ngpu, model):
     output_dir_job = os.path.join(output_dir, "output.{}".format(idx))
-    gpu_id = (int(idx) - 1) // njob
+    if ngpu > 0:
+        use_gpu = 1
+        gpu_id = int(idx) - 1
+    else:
+        use_gpu = 0
+        gpu_id = -1
     if "CUDA_VISIBLE_DEVICES" in os.environ.keys():
         gpu_list = os.environ['CUDA_VISIBLE_DEVICES'].split(",")
         os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_list[gpu_id])
@@ -18,9 +23,10 @@ def modelscope_infer_core(output_dir, split_dir, njob, idx):
         os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_id)
     inference_pipline = pipeline(
         task=Tasks.auto_speech_recognition,
-        model="damo/speech_paraformer-large_asr_nat-zh-cn-16k-aishell2-vocab8404-pytorch",
+        model=model,
         output_dir=output_dir_job,
-        batch_size=64
+        batch_size=batch_size,
+        ngpu=use_gpu,
     )
     audio_in = os.path.join(split_dir, "wav.{}.scp".format(idx))
     inference_pipline(audio_in=audio_in)
@@ -30,13 +36,18 @@ def modelscope_infer(params):
     # prepare for multi-GPU decoding
     ngpu = params["ngpu"]
     njob = params["njob"]
+    batch_size = params["batch_size"]
     output_dir = params["output_dir"]
+    model = params["model"]
     if os.path.exists(output_dir):
         shutil.rmtree(output_dir)
     os.mkdir(output_dir)
     split_dir = os.path.join(output_dir, "split")
     os.mkdir(split_dir)
-    nj = ngpu * njob
+    if ngpu > 0:
+        nj = ngpu
+    elif ngpu == 0:
+        nj = njob
     wav_scp_file = os.path.join(params["data_dir"], "wav.scp")
     with open(wav_scp_file) as f:
         lines = f.readlines()
@@ -56,7 +67,7 @@ def modelscope_infer(params):
     p = Pool(nj)
     for i in range(nj):
         p.apply_async(modelscope_infer_core,
-                      args=(output_dir, split_dir, njob, str(i + 1)))
+                      args=(output_dir, split_dir, njob, str(i + 1), batch_size, ngpu, model))
     p.close()
     p.join()
 
@@ -81,8 +92,10 @@ def modelscope_infer(params):
 
 if __name__ == "__main__":
     params = {}
+    params["model"] = "damo/speech_paraformer-large_asr_nat-zh-cn-16k-aishell2-vocab8404-pytorch"
     params["data_dir"] = "./data/test"
     params["output_dir"] = "./results"
-    params["ngpu"] = 1
-    params["njob"] = 1
-    modelscope_infer(params)
+    params["ngpu"] = 1 # if ngpu > 0, will use gpu decoding
+    params["njob"] = 1 # if ngpu = 0, will use cpu decoding
+    params["batch_size"] = 64
+    modelscope_infer(params)

egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-aishell2-vocab8404-pytorch/infer_after_finetune.py

@@ -4,23 +4,18 @@ import shutil
 
 from modelscope.pipelines import pipeline
 from modelscope.utils.constant import Tasks
+from modelscope.hub.snapshot_download import snapshot_download
 
 from funasr.utils.compute_wer import compute_wer
 
-
 def modelscope_infer_after_finetune(params):
     # prepare for decoding
-    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))
+
+    try:
+        pretrained_model_path = snapshot_download(params["modelscope_model_name"], cache_dir=params["output_dir"])
+    except BaseException:
+        raise BaseException(f"Please download pretrain model from ModelScope firstly.")
+    shutil.copy(os.path.join(params["output_dir"], params["decoding_model_name"]), os.path.join(pretrained_model_path, "model.pb"))
     decoding_path = os.path.join(params["output_dir"], "decode_results")
     if os.path.exists(decoding_path):
         shutil.rmtree(decoding_path)
@@ -29,9 +24,9 @@ def modelscope_infer_after_finetune(params):
     # decoding
     inference_pipeline = pipeline(
         task=Tasks.auto_speech_recognition,
-        model=params["output_dir"],
+        model=pretrained_model_path,
         output_dir=decoding_path,
-        batch_size=64
+        batch_size=params["batch_size"]
     )
     audio_in = os.path.join(params["data_dir"], "wav.scp")
     inference_pipeline(audio_in=audio_in)
@@ -46,8 +41,8 @@ def modelscope_infer_after_finetune(params):
 if __name__ == '__main__':
     params = {}
     params["modelscope_model_name"] = "damo/speech_paraformer-large_asr_nat-zh-cn-16k-aishell2-vocab8404-pytorch"
-    params["required_files"] = ["am.mvn", "decoding.yaml", "configuration.json"]
     params["output_dir"] = "./checkpoint"
     params["data_dir"] = "./data/test"
     params["decoding_model_name"] = "valid.acc.ave_10best.pb"
-    modelscope_infer_after_finetune(params)
+    params["batch_size"] = 64
+    modelscope_infer_after_finetune(params)

egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/README.md

@@ -22,10 +22,12 @@
 Or you can use the finetuned model for inference directly.
 
 - Setting parameters in `infer.py`
+    - <strong>model:</strong> # model name on ModelScope
     - <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
+    - <strong>ngpu:</strong> # the number of GPUs for decoding, if `ngpu` > 0, use GPU decoding
+    - <strong>njob:</strong> # the number of jobs for CPU decoding, if `ngpu` = 0, use CPU decoding, please set `njob`
+    - <strong>batch_size:</strong> # batchsize of inference
 
 - Then you can run the pipeline to infer with:
 ```python
@@ -39,9 +41,11 @@ The decoding results can be found in `$output_dir/1best_recog/text.cer`, which i
 ### Inference using local finetuned model
 
 - Modify inference related parameters in `infer_after_finetune.py`
+    - <strong>modelscope_model_name: </strong> # model name on ModelScope
     - <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`
+    - <strong>batch_size:</strong> # batchsize of inference  
 
 - Then you can run the pipeline to finetune with:
 ```python

egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer.py

@@ -8,9 +8,14 @@ from modelscope.utils.constant import Tasks
 from funasr.utils.compute_wer import compute_wer
 
 
-def modelscope_infer_core(output_dir, split_dir, njob, idx):
+def modelscope_infer_core(output_dir, split_dir, njob, idx, batch_size, ngpu, model):
     output_dir_job = os.path.join(output_dir, "output.{}".format(idx))
-    gpu_id = (int(idx) - 1) // njob
+    if ngpu > 0:
+        use_gpu = 1
+        gpu_id = int(idx) - 1
+    else:
+        use_gpu = 0
+        gpu_id = -1
     if "CUDA_VISIBLE_DEVICES" in os.environ.keys():
         gpu_list = os.environ['CUDA_VISIBLE_DEVICES'].split(",")
         os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_list[gpu_id])
@@ -18,9 +23,10 @@ def modelscope_infer_core(output_dir, split_dir, njob, idx):
         os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_id)
     inference_pipline = pipeline(
         task=Tasks.auto_speech_recognition,
-        model="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch",
+        model=model,
         output_dir=output_dir_job,
-        batch_size=64
+        batch_size=batch_size,
+        ngpu=use_gpu,
     )
     audio_in = os.path.join(split_dir, "wav.{}.scp".format(idx))
     inference_pipline(audio_in=audio_in)
@@ -30,13 +36,18 @@ def modelscope_infer(params):
     # prepare for multi-GPU decoding
     ngpu = params["ngpu"]
     njob = params["njob"]
+    batch_size = params["batch_size"]
     output_dir = params["output_dir"]
+    model = params["model"]
     if os.path.exists(output_dir):
         shutil.rmtree(output_dir)
     os.mkdir(output_dir)
     split_dir = os.path.join(output_dir, "split")
     os.mkdir(split_dir)
-    nj = ngpu * njob
+    if ngpu > 0:
+        nj = ngpu
+    elif ngpu == 0:
+        nj = njob
     wav_scp_file = os.path.join(params["data_dir"], "wav.scp")
     with open(wav_scp_file) as f:
         lines = f.readlines()
@@ -56,7 +67,7 @@ def modelscope_infer(params):
     p = Pool(nj)
     for i in range(nj):
         p.apply_async(modelscope_infer_core,
-                      args=(output_dir, split_dir, njob, str(i + 1)))
+                      args=(output_dir, split_dir, njob, str(i + 1), batch_size, ngpu, model))
     p.close()
     p.join()
 
@@ -81,8 +92,10 @@ def modelscope_infer(params):
 
 if __name__ == "__main__":
     params = {}
+    params["model"] = "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
     params["data_dir"] = "./data/test"
     params["output_dir"] = "./results"
-    params["ngpu"] = 1
-    params["njob"] = 1
-    modelscope_infer(params)
+    params["ngpu"] = 1 # if ngpu > 0, will use gpu decoding
+    params["njob"] = 1 # if ngpu = 0, will use cpu decoding
+    params["batch_size"] = 64
+    modelscope_infer(params)

egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer_after_finetune.py

@@ -4,23 +4,18 @@ import shutil
 
 from modelscope.pipelines import pipeline
 from modelscope.utils.constant import Tasks
+from modelscope.hub.snapshot_download import snapshot_download
 
 from funasr.utils.compute_wer import compute_wer
 
-
 def modelscope_infer_after_finetune(params):
     # prepare for decoding
-    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))
+
+    try:
+        pretrained_model_path = snapshot_download(params["modelscope_model_name"], cache_dir=params["output_dir"])
+    except BaseException:
+        raise BaseException(f"Please download pretrain model from ModelScope firstly.")
+    shutil.copy(os.path.join(params["output_dir"], params["decoding_model_name"]), os.path.join(pretrained_model_path, "model.pb"))
     decoding_path = os.path.join(params["output_dir"], "decode_results")
     if os.path.exists(decoding_path):
         shutil.rmtree(decoding_path)
@@ -29,9 +24,9 @@ def modelscope_infer_after_finetune(params):
     # decoding
     inference_pipeline = pipeline(
         task=Tasks.auto_speech_recognition,
-        model=params["output_dir"],
+        model=pretrained_model_path,
         output_dir=decoding_path,
-        batch_size=64
+        batch_size=params["batch_size"]
     )
     audio_in = os.path.join(params["data_dir"], "wav.scp")
     inference_pipeline(audio_in=audio_in)
@@ -46,8 +41,8 @@ def modelscope_infer_after_finetune(params):
 if __name__ == '__main__':
     params = {}
     params["modelscope_model_name"] = "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
-    params["required_files"] = ["am.mvn", "decoding.yaml", "configuration.json"]
     params["output_dir"] = "./checkpoint"
     params["data_dir"] = "./data/test"
     params["decoding_model_name"] = "valid.acc.ave_10best.pb"
-    modelscope_infer_after_finetune(params)
+    params["batch_size"] = 64
+    modelscope_infer_after_finetune(params)

egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/infer.py

@@ -8,9 +8,14 @@ from modelscope.utils.constant import Tasks
 from funasr.utils.compute_wer import compute_wer
 
 
-def modelscope_infer_core(output_dir, split_dir, njob, idx):
+def modelscope_infer_core(output_dir, split_dir, njob, idx, batch_size, ngpu, model):
     output_dir_job = os.path.join(output_dir, "output.{}".format(idx))
-    gpu_id = (int(idx) - 1) // njob
+    if ngpu > 0:
+        use_gpu = 1
+        gpu_id = int(idx) - 1
+    else:
+        use_gpu = 0
+        gpu_id = -1
     if "CUDA_VISIBLE_DEVICES" in os.environ.keys():
         gpu_list = os.environ['CUDA_VISIBLE_DEVICES'].split(",")
         os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_list[gpu_id])
@@ -18,9 +23,10 @@ def modelscope_infer_core(output_dir, split_dir, njob, idx):
         os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_id)
     inference_pipline = pipeline(
         task=Tasks.auto_speech_recognition,
-        model="damo/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1",
+        model=model,
         output_dir=output_dir_job,
-        batch_size=64
+        batch_size=batch_size,
+        ngpu=use_gpu,
     )
     audio_in = os.path.join(split_dir, "wav.{}.scp".format(idx))
     inference_pipline(audio_in=audio_in)
@@ -30,13 +36,18 @@ def modelscope_infer(params):
     # prepare for multi-GPU decoding
     ngpu = params["ngpu"]
     njob = params["njob"]
+    batch_size = params["batch_size"]
     output_dir = params["output_dir"]
+    model = params["model"]
     if os.path.exists(output_dir):
         shutil.rmtree(output_dir)
     os.mkdir(output_dir)
     split_dir = os.path.join(output_dir, "split")
     os.mkdir(split_dir)
-    nj = ngpu * njob
+    if ngpu > 0:
+        nj = ngpu
+    elif ngpu == 0:
+        nj = njob
     wav_scp_file = os.path.join(params["data_dir"], "wav.scp")
     with open(wav_scp_file) as f:
         lines = f.readlines()
@@ -56,7 +67,7 @@ def modelscope_infer(params):
     p = Pool(nj)
     for i in range(nj):
         p.apply_async(modelscope_infer_core,
-                      args=(output_dir, split_dir, njob, str(i + 1)))
+                      args=(output_dir, split_dir, njob, str(i + 1), batch_size, ngpu, model))
     p.close()
     p.join()
 
@@ -81,8 +92,10 @@ def modelscope_infer(params):
 
 if __name__ == "__main__":
     params = {}
+    params["model"] = "damo/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1"
     params["data_dir"] = "./data/test"
     params["output_dir"] = "./results"
-    params["ngpu"] = 1
-    params["njob"] = 1
-    modelscope_infer(params)
+    params["ngpu"] = 1 # if ngpu > 0, will use gpu decoding
+    params["njob"] = 1 # if ngpu = 0, will use cpu decoding
+    params["batch_size"] = 64
+    modelscope_infer(params)

egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/infer_after_finetune.py

@@ -4,23 +4,18 @@ import shutil
 
 from modelscope.pipelines import pipeline
 from modelscope.utils.constant import Tasks
+from modelscope.hub.snapshot_download import snapshot_download
 
 from funasr.utils.compute_wer import compute_wer
 
-
 def modelscope_infer_after_finetune(params):
     # prepare for decoding
-    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))
+
+    try:
+        pretrained_model_path = snapshot_download(params["modelscope_model_name"], cache_dir=params["output_dir"])
+    except BaseException:
+        raise BaseException(f"Please download pretrain model from ModelScope firstly.")
+    shutil.copy(os.path.join(params["output_dir"], params["decoding_model_name"]), os.path.join(pretrained_model_path, "model.pb"))
     decoding_path = os.path.join(params["output_dir"], "decode_results")
     if os.path.exists(decoding_path):
         shutil.rmtree(decoding_path)
@@ -29,9 +24,9 @@ def modelscope_infer_after_finetune(params):
     # decoding
     inference_pipeline = pipeline(
         task=Tasks.auto_speech_recognition,
-        model=params["output_dir"],
+        model=pretrained_model_path,
         output_dir=decoding_path,
-        batch_size=64
+        batch_size=params["batch_size"]
     )
     audio_in = os.path.join(params["data_dir"], "wav.scp")
     inference_pipeline(audio_in=audio_in)
@@ -46,8 +41,8 @@ def modelscope_infer_after_finetune(params):
 if __name__ == '__main__':
     params = {}
     params["modelscope_model_name"] = "damo/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1"
-    params["required_files"] = ["am.mvn", "decoding.yaml", "configuration.json"]
     params["output_dir"] = "./checkpoint"
     params["data_dir"] = "./data/test"
     params["decoding_model_name"] = "valid.acc.ave_10best.pb"
-    modelscope_infer_after_finetune(params)
+    params["batch_size"] = 64
+    modelscope_infer_after_finetune(params)

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

@@ -4,27 +4,17 @@ import shutil
 
 from modelscope.pipelines import pipeline
 from modelscope.utils.constant import Tasks
+from modelscope.hub.snapshot_download import snapshot_download
 
 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))
+
+    try:
+        pretrained_model_path = snapshot_download(params["modelscope_model_name"], cache_dir=params["output_dir"])
+    except BaseException:
+        raise BaseException(f"Please download pretrain model from ModelScope firstly.")shutil.copy(os.path.join(params["output_dir"], params["decoding_model_name"]), os.path.join(pretrained_model_path, "model.pb"))
     decoding_path = os.path.join(params["output_dir"], "decode_results")
     if os.path.exists(decoding_path):
         shutil.rmtree(decoding_path)
@@ -33,16 +23,16 @@ def modelscope_infer_after_finetune(params):
     # decoding
     inference_pipeline = pipeline(
         task=Tasks.auto_speech_recognition,
-        model=params["output_dir"],
+        model=pretrained_model_path,
         output_dir=decoding_path,
-        batch_size=64
+        batch_size=params["batch_size"]
     )
     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:
+    if os.path.exists(text_in):
         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"))
 
@@ -50,8 +40,8 @@ def modelscope_infer_after_finetune(params):
 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.pb"
-    modelscope_infer_after_finetune(params)
+    params["batch_size"] = 64
+    modelscope_infer_after_finetune(params)