-
**Где нашелся баг**: на sberbox и sberpotal
**Описание проблемы**: При ошибке в передаче [asr_hints](https://developer.sberdevices.ru/docs/ru/platform_services/context_hint) на sberbox и sberpotal ca…
-
I would like to know if it is possible to use CTranslate2 hosted model pipeline linked with a websocket service like twilio to receive audio streams. Like https://github.com/ufal/whisper_streaming or …
-
It seems a good solution for `libasr` is to have one `LCompilers` namespace, and put `ASR` and `ASRUtils` namespaces underneath it.
The two options to consider for LPython and LFortran frontends ar…
-
I have a question about decoder inputs. I think the following pre-processing adds SOS and EOS token to label y.
https://github.com/gentaiscool/end2end-asr-pytorch/blob/a22efdda28f1689206eefb3fedbb56…
-
使用asr接口，调试batch_size并行输出结果。输入相同的数据，在下面的操作中（concat），不同的batch_size发现推理的结果不同。
所作操作：
1.import paddle
from paddlespeech.cli.asr import ASRExecutor
asr_executor = ASRExecutor()
text = asr_executo…
-
Let's take an example of the `StringSection` node. It was introduced in `lpython` and now it is also used in `lfortran`. The current `StringSection` in the LLVM backend is implemented based on 0-based…
-
Building the current branch fails on my system during the compilation of the file
`src/libasr/CMakeFiles/asr.dir/codegen/evaluator.cpp.o`.
The corresponding complete compiler output can be found h…
-
我发现 torchaudio.pipelines.HUBERT_ASR_LARGE输出的音频特征的维度是 (m, 29)， DeepSpeech v0.1输出的音频特征的维度是 (n, 29)，m和n相差不大，Wav2vecDS的作用是将 (m, 29)维度的特征映射到 (n, 29)维度。
我在想是不是可以把 Wav2vecDS做得更加通用一些，支持将任意维度的特征映射到 (n, 29)维度，…
-
Hey guys, I notice there‘s on-the-fly feats in `asr_datamodule.py`:
https://github.com/k2-fsa/icefall/blob/32de2766d591d2e1a77c06a40d2861fb1bbcd3ad/egs/wenetspeech/ASR/pruned_transducer_stateless2/as…
-
Towards #4397
MRE :
```fortran
program bobyqa_exmp
real :: A(2) = [2,2]
logical :: B(2)
B = abs(A) > maxval(abs(A))
end program bobyqa_exmp
```
LFortran Error :
```console
Internal C…