From 0a7c0661b13e299f68c458d19fc766839cd01bfb Mon Sep 17 00:00:00 2001
From: lzr265946 <lzr265946@alibaba-inc.com>
Date: 星期一, 13 二月 2023 11:38:32 +0800
Subject: [PATCH] add paraformer-large-contextual egs_modelscope

---
 egs_modelscope/asr/paraformer/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/README.md |   19 +++++++++++++++++++
 egs_modelscope/asr/paraformer/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/infer.py  |   21 +++++++++++++++++++++
 2 files changed, 40 insertions(+), 0 deletions(-)

diff --git a/egs_modelscope/asr/paraformer/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/README.md b/egs_modelscope/asr/paraformer/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/README.md
new file mode 100644
index 0000000..49c0aeb
--- /dev/null
+++ b/egs_modelscope/asr/paraformer/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/README.md
@@ -0,0 +1,19 @@
+# ModelScope Model
+
+## How to infer using a pretrained Paraformer-large Model
+
+### Inference
+
+You can use the pretrain model for inference directly.
+
+- Setting parameters in `infer.py`
+    - <strong>audio_in:</strong> # Support wav, url, bytes, and parsed audio format.
+    - <strong>output_dir:</strong> # If the input format is wav.scp, it needs to be set.
+    - <strong>batch_size:</strong> # Set batch size in inference.
+    - <strong>param_dict:</strong> # Set the hotword list in inference.
+
+- Then you can run the pipeline to infer with:
+```python
+    python infer.py
+```
+
diff --git a/egs_modelscope/asr/paraformer/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/infer.py b/egs_modelscope/asr/paraformer/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/infer.py
new file mode 100644
index 0000000..78fb8f1
--- /dev/null
+++ b/egs_modelscope/asr/paraformer/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/infer.py
@@ -0,0 +1,21 @@
+from modelscope.pipelines import pipeline
+from modelscope.utils.constant import Tasks
+
+
+if __name__ == '__main__':
+    param_dict = dict()
+    param_dict['hotword'] = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/hotword.txt"
+
+    audio_in = "//isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_hotword.wav"
+    output_dir = None
+    batch_size = 1
+
+    inference_pipeline = pipeline(
+        task=Tasks.auto_speech_recognition,
+        model="damo/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404",
+        output_dir=output_dir,
+        batch_size=batch_size,
+        param_dict=param_dict)
+
+    rec_result = inference_pipeline(audio_in=audio_in)
+    print(rec_result)

--
Gitblit v1.9.1