Merge pull request #540 from alibaba-damo-academy/dev-zc

add speech_UniASR_asr_2pass-tr-16k-common-vocab1582-pytorch

egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-tr-16k-common-vocab1582-pytorch/finetune.py

@@ -0,0 +1,35 @@
+import os
+from modelscope.metainfo import Trainers
+from modelscope.trainers import build_trainer
+from funasr.datasets.ms_dataset import MsDataset
+
+
+def modelscope_finetune(params):
+    if not os.path.exists(params["output_dir"]):
+        os.makedirs(params["output_dir"], exist_ok=True)
+    # dataset split ["train", "validation"]
+    ds_dict = MsDataset.load(params["data_dir"])
+    kwargs = dict(
+        model=params["model"],
+        model_revision=params["model_revision"],
+        data_dir=ds_dict,
+        dataset_type=params["dataset_type"],
+        work_dir=params["output_dir"],
+        batch_bins=params["batch_bins"],
+        max_epoch=params["max_epoch"],
+        lr=params["lr"])
+    trainer = build_trainer(Trainers.speech_asr_trainer, default_args=kwargs)
+    trainer.train()
+
+
+if __name__ == '__main__':
+    params = {}
+    params["output_dir"] = "./checkpoint"
+    params["data_dir"] = "./data"
+    params["batch_bins"] = 2000
+    params["dataset_type"] = "small"
+    params["max_epoch"] = 50
+    params["lr"] = 0.00005
+    params["model"] = "damo/speech_UniASR_asr_2pass-tr-16k-common-vocab1582-pytorch"
+    params["model_revision"] = None
+    modelscope_finetune(params)

egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-tr-16k-common-vocab1582-pytorch/infer.py

@@ -0,0 +1,13 @@
+from modelscope.pipelines import pipeline
+from modelscope.utils.constant import Tasks
+
+if __name__ == "__main__":
+    audio_in = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_tr.wav"
+    output_dir = "./results"
+    inference_pipeline = pipeline(
+        task=Tasks.auto_speech_recognition,
+        model="damo/speech_UniASR_asr_2pass-tr-16k-common-vocab1582-pytorch",
+        output_dir=output_dir,
+    )
+    rec_result = inference_pipeline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
+    print(rec_result)