From 3a4281f4959534b1bf5d01acf0085f4f8e6f2ec8 Mon Sep 17 00:00:00 2001
From: wuhongsheng <664116298@qq.com>
Date: 星期五, 05 七月 2024 00:55:32 +0800
Subject: [PATCH] 优化speakid和语句匹配逻辑，部分解决speakid不从0递增问题 (#1870)
---
examples/industrial_data_pretraining/sense_voice/demo.py | 27 ++++++++++++++-------------
1 files changed, 14 insertions(+), 13 deletions(-)
diff --git a/examples/industrial_data_pretraining/sense_voice/demo.py b/examples/industrial_data_pretraining/sense_voice/demo.py
index 0d8ef97..3635571 100644
--- a/examples/industrial_data_pretraining/sense_voice/demo.py
+++ b/examples/industrial_data_pretraining/sense_voice/demo.py
@@ -3,22 +3,23 @@
# Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.
# MIT License (https://opensource.org/licenses/MIT)
+import sys
from funasr import AutoModel
-model = AutoModel(model="/Users/zhifu/Downloads/modelscope_models/SenseVoiceModelscope",
- vad_model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch",
- vad_kwargs={"max_single_segment_time": 30000},
- )
+model_dir = "iic/SenseVoiceSmall"
+input_file = (
+ "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav"
+)
+model = AutoModel(
+ model=model_dir,
+)
-input_wav = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav"
+res = model.generate(
+ input=input_file,
+ cache={},
+ language="auto", # "zn", "en", "yue", "ja", "ko", "nospeech"
+ use_itn=False,
+)
-DecodingOptions = {
- "task": ("ASR", "AED", "SER"),
- "language": "auto",
- "fp16": True,
- "gain_event": True,
- }
-
-res = model.generate(input=input_wav, batch_size_s=0, DecodingOptions=DecodingOptions)
print(res)
--
Gitblit v1.9.1