Marketplace · Speech-to-text
Systran/faster-whisper-base
Call Systran/faster-whisper-base through one OpenAI-compatible API. It's served by 1 host on the Inpherio grid, each at a price it sets — your request goes to the cheapest healthy one, and fails over to the next if it's down.
At a glance.
multilingual
from openai import OpenAI
client = OpenAI(base_url="https://inpherio.co.uk/v1",
api_key=INPHERIO_API_KEY)
text = client.audio.transcriptions.create(
model="Systran/faster-whisper-base",
file=open("audio.mp3", "rb"),
)Systran/faster-whisper-base in detail.
This repository contains the conversion of [openai/whisper-base](https://huggingface.co/openai/whisper-base) to the [CTranslate2](https://github.com/OpenNMT/CTranslate2) model format.
- Published by
- Systran
- Download size
- 145 MB (weights on Hugging Face)
- Format
- ctranslate2
- Licence
- MIT
- Task
- automatic speech recognition
- Library
- ctranslate2
- Languages
- en, zh, de, es, ru, ko, fr, ja, pt, tr, pl, ca
- First published
- 23 Nov 2023
- Last updated
- 23 Nov 2023
- Downloads (30 days)
- 2.2 million on Hugging Face
- Likes
- 53
ctranslate2 audio automatic-speech-recognition en zh de es ru ko fr ja pt tr pl ca nl
The model card
Published by the model's authors on Hugging Face — shown as they wrote it, unedited by Inpherio.
Whisper base model for CTranslate2
This repository contains the conversion of openai/whisper-base to the CTranslate2 model format.
This model can be used in CTranslate2 or projects based on CTranslate2 such as faster-whisper.
Example
from faster_whisper import WhisperModel
model = WhisperModel("base")
segments, info = model.transcribe("audio.mp3")
for segment in segments:
print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))
Conversion details
The original model was converted with the following command:
ct2-transformers-converter --model openai/whisper-base --output_dir faster-whisper-base \
--copy_files tokenizer.json --quantization float16
Note that the model weights are saved in FP16. This type can be changed when the model is loaded using the compute_type option in CTranslate2.
More information
**For more information about the original model, see its model card.**
Sources: Systran/faster-whisper-base on Hugging Face. Collected from public sources on 8 Nov 2026; the host serving it may run a different build or quantisation — the marketplace shows each host's own measurements.
Who's serving it.
Every host benchmarked this model on its own hardware before serving it. Prices are set by each host; health is scored by the platform from what it observes.
| Host | Tier | Price | Measured speed | Health | State | Rent |
|---|---|---|---|---|---|---|
| GTX 1080 Ti (11G) | L1 | £0.03 /h audio | 5.7× real time | 78 | loads on request | £0.60/h |
Live data, refreshed on every visit. How billing works.
Room on the grid for your machine.
Right now one machine serves Systran/faster-whisper-base. If it drops, so does every request for it — a second host is what turns it into failover, and the grid needs that more than another copy. The router weighs price, measured speed, health and whether the model is already loaded — so a host with a sharper price or quicker hardware wins the next call.
Set your own price — you keep 85% of what it earns, and new hosts start with 12 months fee-free (up to £250 of earnings). A payout fee of £2 + 1% per payout to a UK bank account, £2 + 2% to any other country applies when you're paid. Install the connector, load Systran/faster-whisper-base, and the platform benchmarks it on your hardware before your first request.