Emmanuel Schmidbauer
Emmanuel Schmidbauer
Hi- im trying to get WASM running on my local machine using the latest code (e70e5c8b53faec6abbf0170f1e9a195f4dfccaab) but when i load the page in my browser, i see this issue in...
Hi, thank you for recently adding stereo (dual channel) support. It works great with utterance level timestamps but when i use: `-ml 1` to do word level timestamps, I get...
Hi, I really appreciate you sharing this implementation. I found it to be very fast with accurate results. I do not see word-level timestamps in the result. Are word level...
Hi- appreciate sharing of this framework, it looks very useful I'm wondering if it's possible to do real-time transcriptions using `from transformers.pipelines.audio_utils import ffmpeg_microphone_live` as detailed in this PR: https://github.com/huggingface/transformers/pull/21196
Hello, Is batch execution of faster-whisper's transcribe possible? We've seen in this [thread](https://github.com/OpenNMT/CTranslate2/issues/1119) that batch execution should increase the throughput. But it's not clear how to perform batch using faster-whisper...
vLLM supports an OpenAI-Compatible API. is it possible to configure this code to connect to another service other than OpenAI? I've tried modifying the code but i am getting errors....
when specifying word timestamps on a `3m 45s` file, I am seeing a crash ```sh insanely-fast-whisper --file-name test.wav --timestamp word ``` ```python You are attempting to use Flash Attention 2.0...
Hello, Thank you for sharing this project. I followed the steps in `Whisper Encoder/Decoder training` and was able to train models. The tensorboard looks good as well as the checkpoints...