From 810046e3df4910c8f5c1a90e4b53aca45b3397e8 Mon Sep 17 00:00:00 2001
From: wuhongsheng <664116298@qq.com>
Date: 星期一, 01 七月 2024 10:42:58 +0800
Subject: [PATCH] 优化merge segments 参数，解决新闻联播男女主持人“晚上好”合并一个speakid问题 (#1861)
---
examples/industrial_data_pretraining/paraformer/demo.py | 23 +++++++++++++++--------
1 files changed, 15 insertions(+), 8 deletions(-)
diff --git a/examples/industrial_data_pretraining/paraformer/demo.py b/examples/industrial_data_pretraining/paraformer/demo.py
index f6f4c75..647669f 100644
--- a/examples/industrial_data_pretraining/paraformer/demo.py
+++ b/examples/industrial_data_pretraining/paraformer/demo.py
@@ -14,19 +14,26 @@
)
res = model.generate(
- 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"
-)
-
-res = model.generate(
- input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav"
+ 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
--
Gitblit v1.9.1