Comments (4)
请问有解决办法嘛?我最近也有碰到这个
from funasr.
已解决了,修改三处代码,哪里报错就加一个reshape(-1)
vim /AIproject/ASRTrainer/FunASR-main/funasr/models/transformer/utils/nets_utils.py 197行附近
lengths = lengths.reshape(-1)
vim /AIproject/ASRTrainer/FunASR-main/funasr/models/contextual_paraformer/decoder.py 283行附近
ys_in_lens = ys_in_lens.reshape(-1)
vim /AIproject/ASRTrainer/FunASR-main/funasr/models/paraformer/cif_predictor.py 560行附近
token_length = token_length.reshape(-1)
from funasr.
大佬,问一下哈,底层原因是什么呢?
已解决了,修改三处代码,哪里报错就加一个reshape(-1) vim /AIproject/ASRTrainer/FunASR-main/funasr/models/transformer/utils/nets_utils.py 197行附近 lengths = lengths.reshape(-1) vim /AIproject/ASRTrainer/FunASR-main/funasr/models/contextual_paraformer/decoder.py 283行附近 ys_in_lens = ys_in_lens.reshape(-1) vim /AIproject/ASRTrainer/FunASR-main/funasr/models/paraformer/cif_predictor.py 560行附近 token_length = token_长度.重塑(-1)
from funasr.
Refere
tensor张量维度不符合后续处理要求,这些length应该是一个一维张量,但是只有一个样本的时候,他是一个int型张量,没有维度了,reshape(-1)加一个维度就可以了
from funasr.
Related Issues (20)
- How to create audio profiles for speakers for re-identification?
- 有没有说话人身份识别的例子 HOT 1
- TeleSpeech-ASR1.0对方言支持的比较好,建议将这个模型添加到funasr中使用 HOT 1
- 将识别token和encoder的alpha进行强制对齐的可视化脚本
- funasr-runtime-sdk-online-cpu-0.1.10软件包内存一直缓慢涨,不下降 HOT 3
- 如何训练标点预测模型
- 调用FunASR/runtime/http服务出现错误 basic_string::_M_construct null not valid
- 尝试使用 finetune.sh 微调 seaco-paraformer ,微调后发现,每个epoch 的model.pt增大了很大,从原模型的800多M,增大到了2.44GB多,这是什么原因
- 微信群已经不能扫码加入了
- 导入funasr包时间过长
- 没有 raw_text 这个key
- torch.save保存时没有model.state_dict()
- 如何在funasr-runtime-sdk-cpu-0.4.4 websocket服务端上开启说话人识别? HOT 1
- funasr音频问题
- model.generate传入文件路径和传入文件bytes返回完全不同 HOT 4
- UniASR. 模型 支持转为onnx格式吗 HOT 1
- 通过上传文件识别 无法结束问题
- finetune时的学习率问题,经过初始lr经过scheduler后变得特别小
- paraformer onnx-gpu耗时过长原因定位 HOT 1
- 模型输出的文本和时间戳长度不同,如何进行对应?
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from funasr.