From 28ccfbfc51068a663a80764e14074df5edf2b5ba Mon Sep 17 00:00:00 2001
From: kongdeqiang <kongdeqiang960204@163.com>
Date: 星期五, 13 三月 2026 17:41:41 +0800
Subject: [PATCH] 提交
---
examples/industrial_data_pretraining/paraformer/demo.py | 35 ++++++++++++++++++++++++++++++-----
1 files changed, 30 insertions(+), 5 deletions(-)
diff --git a/examples/industrial_data_pretraining/paraformer/demo.py b/examples/industrial_data_pretraining/paraformer/demo.py
index 6dbe33d..647669f 100644
--- a/examples/industrial_data_pretraining/paraformer/demo.py
+++ b/examples/industrial_data_pretraining/paraformer/demo.py
@@ -5,18 +5,43 @@
from funasr import AutoModel
-model = AutoModel(model="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch", model_revision="v2.0.2")
+model = AutoModel(
+ model="iic/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch",
+ vad_model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch",
+ vad_kwargs={"max_single_segment_time": 60000},
+ punc_model="iic/punc_ct-transformer_zh-cn-common-vocab272727-pytorch",
+ # spk_model="iic/speech_campplus_sv_zh-cn_16k-common",
+)
-res = model(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav")
+res = model.generate(
+ input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav",
+ cache={},
+)
+
print(res)
+""" call english model like below for detailed timestamps
+# choose english paraformer model first
+# iic/speech_paraformer_asr-en-16k-vocab4199-pytorch
+res = model.generate(
+ input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_en.wav",
+ cache={},
+ pred_timestamp=True,
+ return_raw_text=True,
+ sentence_timestamp=True,
+ en_post_proc=True,
+)
+"""
+
+""" can not use currently
from funasr import AutoFrontend
-frontend = AutoFrontend(model="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch", model_revision="v2.0.2")
+frontend = AutoFrontend(model="iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch")
fbanks = frontend(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav", batch_size=2)
for batch_idx, fbank_dict in enumerate(fbanks):
- res = model(**fbank_dict)
- print(res)
\ No newline at end of file
+ res = model.generate(**fbank_dict)
+ print(res)
+"""
--
Gitblit v1.9.1