-
**Problem with decode result on SPGISpeech dataset**
Hi, I downloaded the pretrained model from [https://zenodo.org/record/4585546](https://zenodo.org/record/4585546) and inference with differe…
-
### 🚀 The feature
Consider on-boarding aligner from [Huang et al., Less Peaky and More Accurate CTC Forced Alignment by Label Priors](https://arxiv.org/abs/2406.02560) (@huangruizhe) to the existin…
-
Hi, thank you for publishing such a great work!
I just want to make sure whether the customized My_WavVec2CTCTokenizer is a phoneme-level tokenizer, which contains only phoneme inventory. In the file…
-
With:
* https://github.com/pytorch/pytorch/commit/cd472bb1e368a711a2bd34d5671c77dab336d312
* Plus this applied: https://github.com/pytorch/pytorch/pull/135567
* https://github.com/intel/torch-xpu…
-
### Describe the bug
I trained several ASR models using different SSL models ([facebook/hubert-base-ls960](https://huggingface.co/facebook/hubert-base-ls960), [Orange/SSA-HuBERT-base-60k](https://h…
-
Hi, how to calibrate bonito trained models so base qualities correspond to expected error rate?
For example `config.toml` for RNA004 sup models uses:
```bash
[qscore]
scale = 0.9
bias = -0.1
…
-
why my task.target_dictionary.indices have a space !!!!
{'': 0, '': 1, '': 2, '': 3, '| ': 4, 'E ': 5, 'A ': 6, 'T ': 7, 'R ': 8, 'O ': 9, 'S ': 10, 'I ': 11, 'N ': 12, 'H ': 13, 'L ': 14, 'D ': 15, …
-
reproduce:
```
wget https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-streaming-paraformer-bilingual-zh-en.tar.bz2
tar xvf sherpa-onnx-streaming-paraformer-bili…
-
Please:
- [x] Check for duplicate requests.
- [x] Describe your goal, and if possible provide a code snippet with a motivating example.
## Community Request for JAX CTC Loss
First of all, I'…
-
Hi, I'm encountering the following error while following the usage of the command. Could anyone kindly help me resolve this issue? I would really appreciate any assistance. Thank you!
Below are the…