From c9322bbe5a4f09680f667870aaadbb96025724f7 Mon Sep 17 00:00:00 2001
From: chong.zhang <chong.zhang@alibaba-inc.com>
Date: 星期二, 23 五月 2023 15:03:18 +0800
Subject: [PATCH] add speech_UniASR_asr_2pass-ur-16k-common-vocab877-pytorch
---
egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-tr-16k-common-vocab1582-pytorch/infer.py | 13 +++++++++++++
egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-tr-16k-common-vocab1582-pytorch/finetune.py | 35 +++++++++++++++++++++++++++++++++++
2 files changed, 48 insertions(+), 0 deletions(-)
diff --git a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-tr-16k-common-vocab1582-pytorch/finetune.py b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-tr-16k-common-vocab1582-pytorch/finetune.py
new file mode 100644
index 0000000..850cedc
--- /dev/null
+++ b/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)
diff --git a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-tr-16k-common-vocab1582-pytorch/infer.py b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-tr-16k-common-vocab1582-pytorch/infer.py
new file mode 100644
index 0000000..07a6233
--- /dev/null
+++ b/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)
--
Gitblit v1.9.1