-
Hi Quan,
I was trying to train an ASR system on WSJ using your toolkit using the similar setup as your ICASSP paper on the swbd corpus. If fbank features are used, the training and decoding work fine…
-
Hi, I'm unable to run sherpa through python (though command line `sherpa-offline` works).
I'm copying the code exactly as on the colaboratory yet the script crashes on these lines:
```python
f…
-
In https://github.com/conda-forge/torchaudio-feedstock/pull/4, I see the following kind of lines
```
│ │ │ =========================== short test summary info ============================
│ │ │ FAIL…
-
The UG states that the command parameters can be in any order.
I tried a…
-
HI,
I'm trying to fine-tune PASE+ model on my own dataset, but it seems that I'm getting this error for the training script. I was able to correctly produce the stats file and .scp files with the p…
-
https://github.com/lovemefan/telespeech-asr-python
感谢官方团队开源，如果可以的话，希望能够后续能够pr合并
-
When a `buid-ios.sh` trying to create headers for build/simulator/lib it encounters an error like:
`fatal error: /Applications/Xcode.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin…
-
### Describe the bug
For a real time project, I need to convert [Spkrec-Ecapa-voxceleb](https://huggingface.co/speechbrain/spkrec-ecapa-voxceleb) to ONNX in order to use it in cpp with [OnnxRuntime…
-
I observe that exetacting MFCC or MFB features utilizes almost all the CPU with 100% capacity. I am sure that extracting these features doesn't requires so much of computation.
I am processing onl…
-
Hi Yuan!
Thanks again for this next iteration of the model - it was the improvement that I was hoping for in our task!
I have a quick question regarding normalization. You mention in your AST pa…