From 72c8f70ef470a878901dedb575081660ac474133 Mon Sep 17 00:00:00 2001
From: onlybetheone <iriszhangchong@gmail.com>
Date: 星期五, 10 三月 2023 18:08:18 +0800
Subject: [PATCH] add egs_modelscope/uniasr/ he my ur examples
---
egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-he-16k-common-vocab1085-pytorch/infer.py | 13 ++++
egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-my-16k-common-vocab696-pytorch/finetune.py | 35 +++++++++++
egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-ur-16k-common-vocab877-pytorch/finetune.py | 35 +++++++++++
egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-he-16k-common-vocab1085-pytorch/finetune.py | 35 +++++++++++
egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-my-16k-common-vocab696-pytorch/infer.py | 13 ++++
egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-ur-16k-common-vocab877-pytorch/infer.py | 13 ++++
6 files changed, 144 insertions(+), 0 deletions(-)
diff --git a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-he-16k-common-vocab1085-pytorch/finetune.py b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-he-16k-common-vocab1085-pytorch/finetune.py
new file mode 100644
index 0000000..56fb583
--- /dev/null
+++ b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-he-16k-common-vocab1085-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-he-16k-common-vocab1085-pytorch"
+ params["model_revision"] = None
+ modelscope_finetune(params)
diff --git a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-he-16k-common-vocab1085-pytorch/infer.py b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-he-16k-common-vocab1085-pytorch/infer.py
new file mode 100644
index 0000000..c54ab8c
--- /dev/null
+++ b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-he-16k-common-vocab1085-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_he.wav"
+ output_dir = "./results"
+ inference_pipline = pipeline(
+ task=Tasks.auto_speech_recognition,
+ model="damo/speech_UniASR_asr_2pass-he-16k-common-vocab1085-pytorch",
+ output_dir=output_dir,
+ )
+ rec_result = inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
+ print(rec_result)
diff --git a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-my-16k-common-vocab696-pytorch/finetune.py b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-my-16k-common-vocab696-pytorch/finetune.py
new file mode 100644
index 0000000..8bbce60
--- /dev/null
+++ b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-my-16k-common-vocab696-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-my-16k-common-vocab696-pytorch"
+ params["model_revision"] = None
+ modelscope_finetune(params)
diff --git a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-my-16k-common-vocab696-pytorch/infer.py b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-my-16k-common-vocab696-pytorch/infer.py
new file mode 100644
index 0000000..cfd869f
--- /dev/null
+++ b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-my-16k-common-vocab696-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_my.wav"
+ output_dir = "./results"
+ inference_pipline = pipeline(
+ task=Tasks.auto_speech_recognition,
+ model="damo/speech_UniASR_asr_2pass-my-16k-common-vocab696-pytorch",
+ output_dir=output_dir,
+ )
+ rec_result = inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
+ print(rec_result)
diff --git a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-ur-16k-common-vocab877-pytorch/finetune.py b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-ur-16k-common-vocab877-pytorch/finetune.py
new file mode 100644
index 0000000..5e313e5
--- /dev/null
+++ b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-ur-16k-common-vocab877-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-ur-16k-common-vocab877-pytorch"
+ params["model_revision"] = None
+ modelscope_finetune(params)
diff --git a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-ur-16k-common-vocab877-pytorch/infer.py b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-ur-16k-common-vocab877-pytorch/infer.py
new file mode 100644
index 0000000..e8c5524
--- /dev/null
+++ b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-ur-16k-common-vocab877-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_ur.wav"
+ output_dir = "./results"
+ inference_pipline = pipeline(
+ task=Tasks.auto_speech_recognition,
+ model="damo/speech_UniASR_asr_2pass-ur-16k-common-vocab877-pytorch",
+ output_dir=output_dir,
+ )
+ rec_result = inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
+ print(rec_result)
--
Gitblit v1.9.1