Model reference · open weights
distil-large is an open-weight audio or speech model from distil-whisper, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
Distil-Whisper: distil-large-v3 Distil-Whisper was proposed in the paper Robust Knowledge Distillation via Large-Scale Pseudo Labelling. This is the third and final installment of the Distil-Whisper English series. It the knowledge distilled version of OpenAI's Whisper large-v3, the latest and most performant Whisper model to date. Compared to previous Distil-Whisper models, the distillation procedure for distil-large-v3 has been adapted to give superior long-form transcription accuracy with OpenAI's sequential long-form algorithm. The result is a distilled model that performs to within 1% WER of large-v3 on long-form audio using both the sequential and chunked algorithms, and outperforms distil-large-v2 by 4.8% using the sequential algorithm. The model is also faster than previous Distil-Whisper models: 6.3x faster than large-v3, and 1.1x faster than distil-large-v2. Since the sequential algorithm is the "de-facto" transcription algorithm across the most popular Whisper libraries (Whisper cpp, Faster-Whisper, OpenAI Whisper), this distilled model is designed to be compatible with these libraries. You can expect significant performance gains by switching from previous Distil-Whisper checkpoints to distil-large-v3 when using these libraries. For convenience, the weights for the most popular libraries are already converted, with instructions for getting started below. Table of Contents 1. Transformers Usage Short-Form Transcription Sequential Long-Form Chunked Long-Form Speculative Decoding Additional Speed and Memory Improvements 2. Library Integrations Whisper cpp Faster Whisper OpenAI Whisper Transformers.js Candle 3. Model Details 4. License Transformers Usage distil-large-v3 is supported in the Hugging Face 🤗 Transformers library from version 4.39 onwards. To run the model, first install the latest version of Transformers. For this example, we'll also install 🤗 Datasets to load a toy audio dataset from the Hugging Face Hub: Short-Form Transcription The model can be used with the pipeline class to transcribe short-form audio files (< 30-seconds) as follows: To transcribe a local audio file, simply pass the path to your audio file when you call the pipeline: Fo
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | distil-whisper |
|---|---|
| Type | Audio & music |
| Parameters (lead) | 756M |
| Variants | 1 |
| Runs with | transformers |
| Released | 2024-03-21 |
| Popularity | 723k downloads / month |
| Likes | 379 |
| Licence | Open weights |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| distil-large-v3 | 756M | BF16 | ~1.7 GB | ✓ | Weights ↗ |
Using it via the API
Once AxForge deploys distil-large for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (distil-large below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/audio/transcriptions \ -H "Authorization: Bearer $AXFORGE_API_KEY" \ -F model="distil-large" -F file=@audio.mp3
Licence
Open weights under mit — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗