Model reference · open weights
faster-whisper.en is an open-weight audio or speech model from Systran, 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
Whisper base.en model for CTranslate2 This repository contains the conversion of openai/whisper-base.en to the CTranslate2 model format. This model can be used in CTranslate2 or projects based on CTranslate2 such as faster-whisper. Example Conversion details The original model was converted with the following command: Note that the model weights are saved in FP16. This type can be changed when the model is loaded using the computetype option in CTranslate2. More information For more information about the original model, see its model card.
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | Systran |
|---|---|
| Type | Audio & music |
| Variants | 1 |
| Runs with | ctranslate2 |
| Released | 2023-11-23 |
| Popularity | 416k downloads / month |
| Likes | 7 |
| 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 |
|---|---|---|---|---|---|
| faster-whisper-base.en | — | BF16 | — | — | Weights ↗ |
Using it via the API
Once AxForge deploys faster-whisper-en for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (faster-whisper-en 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="faster-whisper-en" -F file=@audio.mp3
Details
Languages
Tags
Licence
Open weights under mit — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗