-
I am running jetson voice container follow [https://ngc.nvidia.com/catalog/containers/nvidia:jetson-voice](url)
I tried 2 difference micro devices (micro usb and micro built in usb camera) but they…
-
Hi,
I want to finetune the ASR on the custom dataset, so 2 issues have arisen：
1.How can I do the finetuning for ASR? Is it possible to make modifications only on finetune.py? How can I make modific…
-
I've successfully trained a streaming transformer for German with 13000 hours of data and end-to-end punctuation. See https://huggingface.co/speechcatcher/speechcatcher_german_espnet_streaming_transfo…
-
#17
在会议场景中启动服务并记录了一个小时，总体内存、显存用量和 CPU 、 GPU 占用都维持在较为稳定的状态，这非常好。
不过，在测试中也暴露出一些问题：
- `vad` 截断异常
使用正常大小的声音说 `vad测试` 或者 `ok` ，有很大可能会得到 `bad测试` 和 `k` ，同时在测试中大量出现结尾的一两个字识别不到，表明 `vad` 截断还需改进。
…
-
* cloud ASR will allowed only for specific organizations or customers; all others will be blocked;
* toggle access and visibility in Connect only for enabled organizations or customers; rest should no…
-
I followed all the steps.
apache2 is correctly installed
after running
**/apiai/asr-server/fcgi-nnet3-decoder --fcgi-socket=:8000**
m getting the following output on terminal
/apiai/asr-server/…
-
**MRE**
```fortran
PROGRAM example
integer :: i
integer ::arr(4)
arr = ( i , i = 1, 4 )
print *,arr
END PROGRAM example
```
**GFortran Error**
```shell
tt4.f90:7:17…
-
环境：
PaddlePaddle 2.2.0
Python 3.8(ubuntu18.04)
Cuda 11.2
ASR和TTS在开启第一个后，再打开另一个后报错，该怎么处理？
root@autodl-container-085311853c-b00a9bac:~/PaddleSpeech# paddlespeech_server start --config_file ./demo…
-
Currently the logic in `verify_args` is almost exactly identical to the error checking in the `create_*` functions. Let's figure out how to unify it. Some ideas:
* There will be just one verify/che…
-
Hi,
I an my colleagues have faced the problem of appearing NANs in CTC loss and interruption of training due to too much infinite gradients when training Zipformer on our data.
After some debuggi…