From 8dab6d184a034ca86eafa644ea0d2100aadfe27d Mon Sep 17 00:00:00 2001
From: jmwang66 <wangjiaming.wjm@alibaba-inc.com>
Date: 星期二, 09 五月 2023 10:58:33 +0800
Subject: [PATCH] Merge pull request #473 from alibaba-damo-academy/dev_smohan
---
egs_modelscope/asr_vad_punc/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer.py | 31 ++++++++++++++++++++++---------
1 files changed, 22 insertions(+), 9 deletions(-)
diff --git a/egs_modelscope/asr_vad_punc/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer.py b/egs_modelscope/asr_vad_punc/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer.py
index 2703c2a..5bc205c 100644
--- a/egs_modelscope/asr_vad_punc/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer.py
+++ b/egs_modelscope/asr_vad_punc/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer.py
@@ -1,15 +1,28 @@
+import os
+import shutil
+import argparse
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_zh.wav'
- output_dir = None
- inference_pipline = pipeline(
+def modelscope_infer(args):
+ os.environ['CUDA_VISIBLE_DEVICES'] = str(args.gpuid)
+ inference_pipeline = pipeline(
task=Tasks.auto_speech_recognition,
- model="damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch",
- output_dir=output_dir,
- batch_size=1,
+ model=args.model,
+ output_dir=args.output_dir,
+ batch_size=args.batch_size,
+ param_dict={"decoding_model": args.decoding_mode, "hotword": args.hotword_txt}
)
- rec_result = inference_pipline(audio_in=audio_in)
- print(rec_result)
+ inference_pipeline(audio_in=args.audio_in)
+if __name__ == "__main__":
+ parser = argparse.ArgumentParser()
+ parser.add_argument('--model', type=str, default="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch")
+ parser.add_argument('--audio_in', type=str, default="./data/test/wav.scp")
+ parser.add_argument('--output_dir', type=str, default="./results/")
+ parser.add_argument('--decoding_mode', type=str, default="normal")
+ parser.add_argument('--hotword_txt', type=str, default=None)
+ parser.add_argument('--batch_size', type=int, default=64)
+ parser.add_argument('--gpuid', type=str, default="0")
+ args = parser.parse_args()
+ modelscope_infer(args)
--
Gitblit v1.9.1