-
### 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…
-
**How can we improve our ASR model to reliably output an empty string for unintelligible speech in noisy environments?**
We have trained an ASR model on a Hindi-English mixed dataset comprising app…
-
I’m currently working on finetuning your OWSM-CTC model on a custom dataset, but I’ve encountered some challenges. It seems that finetuning OWSM-CTC differs from the standard OWSM finetuning process, …
-
**Describe the bug**
When training ASR models, it calls "on_save_checkpoint" 2 times in a row. It is unnecessary and can take some time. It is visible when you use "always_save_nemo": True and "save_…
-
**Describe the bug**
A clear and concise description of what the bug is.
I am using nemo inside docker environment, with single GPU, unable to get the ASR ouput using canary 1b model
```
Error exec…
-
### Question
I'm trying to get ASR + segmentation to run on a mobile phone (Pixel 6A, 6GB ram). This time on Brave mobile ;-)
ASR alone works fine. But I have a question about also getting the s…
-
Hello, thank you very much for your work. I would like to reproduce the ASR performance of the AnyGPT Base model on the Librispeech test clean. I noticed that your paper stated a WER of 8.5, but my te…
-
@sanchit-gandhi
Where can I find faster-whisper model evaluation metrics? I don't see them on ASR leaderboard. Thanks!
-
Hi,
I am trying to make working canary-1b on long audio file. Inspiring my self from [https://github.com/NVIDIA/NeMo/blob/b5798ded9f27168db9d7d77cbe4f9da80bf49268/examples/asr/asr_chunked_inference/ae…
-
Can I open a PR to add the latest version of faster-whisper in reqs? I have updated asr.py to account for the new parameters needed in default_asr_options in faster_whisper.transcribe.TranscriptionOpt…