-
问题: 转文字的结果中出现非常多的「曩」字
问题截图:
![image](https://github.com/alibaba-damo-academy/FunASR/assets/5625783/fff58604-4ce4-4685-be6f-213d3e102027)
代码版本: FunASR-10 branch
原始音频链接: https://www.youtube.…
-
你好,在运行程序时有以下报错,好像是安装包版本的问题
run_audio.sh Stage 1: Prepare input wavs...
--2024-03-04 12:49:43-- https://modelscope.cn/api/v1/models/damo/speech_campplus_speaker-diarization_common/repo?Revision=mast…
-
## 🐛 Bug
使用长音频离线英文版推理报错
脚本文件为:
`
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks
inference_pipeline = pipeline(
task=Tasks.auto_speech_recogn…
-
执行asr 报错
KeyError: 'funasr-pipeline is not in the pipelines registry group auto-speech-recognition. Please make sure the correct version of ModelScope library is used.'
怎么解决
-
## 🐛 Bug
FunASR/funasr/auto/auto_model.py
inference_with_vad函数中, 当分段结果为0时,time_speech_total_all_samples会除零异常
### To Reproduce
Steps to reproduce the behavior (**always include the command …
-
这段代码:
```
from funasr import AutoModel
model = AutoModel(
model="damo/speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch",
model_revision="v2.0.0",
vad_model=…
-
Hi, My name is Nathan and i try to do training part according to "wespeaker/examples/voxceleb/v2".
I got few error.
1. [Errno 28] No space left on device.
2. [error] checkpoint is null !
My env …
-
## 问题描述
使用 SV 进行声纹验证,一段音频是存在人声的音频,另一段音频几乎没有声音(没有人声)。验证结果应该是低于阈值 0.6,但是结果却是高于0.6。想问下对于模型的识别结果,能获取到判断依据么?另外这个 threshold 一般应该设置多少合适?
## 使用模型
damo/speech_campplus_sv_cn_cnceleb_16k
## 识别结果
{'scor…
-
你好,请问这个SeACo模型和论文发布的是同一个么?
我直接使用v2.0.4 在Aishell1的dev上测试并没有达到论文中声称的效果
-
## 🐛 Bug
AttributeError: FunASRPipeline: GenericFunASR: 'CharTokenizer' object has no attribute 'token_list'
### To Reproduce
1. Run python
get error by running pipeline as follows:
path_asr…