From ac6afabdd1e8843a12b7c66dd73538eea461a79a Mon Sep 17 00:00:00 2001
From: shixian.shi <shixian.shi@alibaba-inc.com>
Date: 星期二, 10 十月 2023 15:06:09 +0800
Subject: [PATCH] update paraformer-speaker pipeline
---
egs_modelscope/asr_vad_spk/speech_paraformer-large-vad-punc-spk_asr_nat-zh-cn/demo.py | 17 +++++++++++++++++
funasr/bin/asr_inference_launch.py | 7 +++----
2 files changed, 20 insertions(+), 4 deletions(-)
diff --git a/egs_modelscope/asr_vad_spk/speech_paraformer-large-vad-punc-spk_asr_nat-zh-cn/demo.py b/egs_modelscope/asr_vad_spk/speech_paraformer-large-vad-punc-spk_asr_nat-zh-cn/demo.py
new file mode 100644
index 0000000..a3773b4
--- /dev/null
+++ b/egs_modelscope/asr_vad_spk/speech_paraformer-large-vad-punc-spk_asr_nat-zh-cn/demo.py
@@ -0,0 +1,17 @@
+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/vad_example.wav'
+ output_dir = "./results"
+ inference_pipeline = pipeline(
+ task=Tasks.auto_speech_recognition,
+ model='damo/speech_paraformer-large-vad-punc-spk_asr_nat-zh-cn',
+ vad_model='damo/speech_fsmn_vad_zh-cn-16k-common-pytorch',
+ #punc_model='damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch',
+ punc_model='damo/punc_ct-transformer_cn-en-common-vocab471067-large',
+ output_dir=output_dir,
+ )
+ rec_result = inference_pipeline(audio_in=audio_in, batch_size_token=5000, batch_size_token_threshold_s=40, max_single_segment_time=6000)
+ print(rec_result)
+
diff --git a/funasr/bin/asr_inference_launch.py b/funasr/bin/asr_inference_launch.py
index 15dbdd4..f4140e1 100644
--- a/funasr/bin/asr_inference_launch.py
+++ b/funasr/bin/asr_inference_launch.py
@@ -787,7 +787,7 @@
time_stamp_writer: bool = True,
punc_infer_config: Optional[str] = None,
punc_model_file: Optional[str] = None,
- sv_model_file: Optional[str] = None,
+ sv_model_file: Optional[str] = "~/.cache/modelscope/hub/damo/speech_paraformer-large-vad-punc-spk_asr_nat-zh-cn/campplus_cn_common.bin",
streaming: bool = False,
embedding_node: str = "resnet1_dense",
sv_threshold: float = 0.9465,
@@ -933,7 +933,7 @@
##### speaker_verification #####
##################################
# load sv model
- sv_model_dict = torch.load(sv_model_file, map_location=torch.device('cpu'))
+ sv_model_dict = torch.load(sv_model_file.replace("~", os.environ['HOME']), map_location=torch.device('cpu'))
sv_model = CAMPPlus()
sv_model.load_state_dict(sv_model_dict)
sv_model.eval()
@@ -1084,7 +1084,6 @@
logging.info("decoding, utt: {}, predictions: {}".format(key, text_postprocessed_punc))
torch.cuda.empty_cache()
distribute_spk(asr_result_list[0]['sentences'], sv_output)
- import pdb; pdb.set_trace()
return asr_result_list
return _forward
@@ -2030,7 +2029,7 @@
return inference_paraformer(**kwargs)
elif mode == "paraformer_streaming":
return inference_paraformer_online(**kwargs)
- elif mode == "paraformer_vad_speaker":
+ elif mode.startswith("paraformer_vad_speaker"):
return inference_paraformer_vad_speaker(**kwargs)
elif mode.startswith("paraformer_vad"):
return inference_paraformer_vad_punc(**kwargs)
--
Gitblit v1.9.1