-
Hi, I am faced with a problem when I execute this model in the last step, I don't have any ctc value and I don't have any result of predicted value, any help please,
this is the result:
ori…
-
### Your Feature Request
I am looking to try a few beam searches implementations and i was wondering is there any command to get the ctc output before the encoding to strings?
-
**请将下面信息填写完整，便于我们快速解决问题，谢谢！**
**问题描述**
ch_ppocr_server_v1.1_rec_infer转onnx时，lstm和ctc_align算子不支持，且用户必须使用该版本。
**更多信息 :**
- 模型链接: https://paddleocr.bj.bcebos.com/20-09-22/server/rec/ch_ppocr_s…
-
在新的fork里练了一个模型，借这里宣传一下：https://github.com/Hovennnnn/PKUAutoElective
## 特点
- 模型架构：使用CNN+LSTM+CTC的模型来识别不定长验证码
- 数据集：采用kaptcha生成74.5w张图片
- 识别时间：5-20ms
- 使用[dddd_trainer](https://github.com/sml2h3/dd…
-
Hi Yajie
Thank you very much for your kindly replying..
I want to ask another question: Current Eessen performs best with CMVN and biLSTM, but in real scenario it would take too much time to wait fo…
-
I'm just transfer from tensorflow to pytorch, the module works perfectly fine when I ran on CPU, but I got the exception when I ran on GPU. Here is the stack:
RuntimeError
Expected !pre_compute_inpu…
-
> ('seq_len : ', 100)
('seq_len : ', 100)
[02:42:42] e:\work\testroot\mxnet\src\operator\./cudnn_algoreg-inl.h:106: Runnin
g performance tests to find the best convolution algorithm, this can take …
-
Issue for tracking and coordinating mlx backend work:
### `mlx.math`
- [ ] `fft`
- [ ] `fft2`
- [ ] `rfft`
- [ ] `irfft`
- [ ] `stft`
- [ ] `istft`
- [x] `logsumexp` #19578
- [ ] `qr`…
-
Hi, all
Can the conformer-ctc **phone-based** ASR model be trained by a training graph with a lexicon, which has optional silence in it? So there will be some extra silence tokens in the text like …
-
代码里面在把数据传入LSTM网络的时候把batch_size变换到了第1维（0开始），DataParallel默认按照第0维进行拆分和拼接。
所以第一种方法可以临时修改DataParallel中gather函数传入的参数dim改成1，即可解决，但是跑别的代码要记得改回来。
另一种方法可以将模型的最后输出batch_size改到第0维，这样并行就会按照batch_size拼接，然后再变换…