Shashi Kant

Hi @colinator can you run some WER checks on medium and medium.en models for TensorRT-LLM backend? According to TensorRT-LLM repo, they only support large model. You can use these to...

> Do have a script that performs WER calculation from the csv outputs? I see your WER function, but am not totally clear on any pre-processing (lowercasing, etc) you do...

Hi @colinator any update?

Hi @nexuslux thanks for the interest. Speaker diarization is not planned somewhere near, I may add it later on. Current priorities are: - WhisperS2T-Server - Improve TensorRT-LLM backend. - Explore...

I think whisper.cpp does not support batching. Do you know of any community implementation for batched whisper.cpp ?

Hi @joaogabrieljunq This project is more inclined toward offline ASR. Though I have some plans to work on streaming ASR using whisper in the future. Doing streaming ASR with whisper...

@OValery16 https://github.com/NVIDIA/TensorRT-LLM/issues/1127

Hi @yuekaizhang thanks for showing interest in this project! > If you're not in a hurry, I will be available to help you after 20 days. Yeah no hurry.. I...

Hey @sanchit-gandhi ! You can prepare the benchmark env using this script: [https://github.com/shashikg/WhisperS2T/blob/main/prepare_benchmark_env.sh](https://github.com/shashikg/WhisperS2T/blob/main/prepare_benchmark_env.sh). This will download the required datasets. Please also check these numbers for distil-whisper: [https://github.com/shashikg/WhisperS2T/releases/tag/v1.1.0](https://github.com/shashikg/WhisperS2T/releases/tag/v1.1.0) > Once we...

Hi @brunjo, yes, if you don't provide the language, it will fall back to English. I'll try adding that. However, the issue with this approach is that it complicates the...