ST

stt en fastconformer ctc large

SttGGUF by cstrUpdated 2026-08-02
Download on Hugging Face
Parameters116M
Context—
Layers—
Architecturecanary-ctc
Smallest quant0.1 GB
Quick answer

stt en fastconformer ctc large needs about 0.6 GB of memory at Q5_0 (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 0.1 GB (Q4_K) to 0.2 GB (F16).

FastConformer CTC Large for English speech transcription

This model transcribes speech in lower case English alphabet. It is a "large" version of FastConformer CTC with around 115M parameters. The model accepts 16000 Hz mono‑channel wav files and outputs a transcribed string.

Good at

  • Low‑latency speech transcription
  • Large‑domain English datasets
  • Consistent CTC decoding

Limits

  • No vision support
  • Only English language
  • Requires 8k context for memory estimates

Best for

  • Transcribing podcasts
  • Voice‑to‑text for customer support
  • Generating subtitles for videos

Who it’s for. Users needing accurate English speech recognition in a lightweight format. Suitable for developers integrating ASR into applications or researchers fine‑tuning on specific audio domains.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K0.1 GB 0.6 GB
Fits Get file →
Q5_00.1 GB 0.6 GB
Fits Get file →
Q8_00.1 GB 0.6 GB
Fits Get file →
F160.2 GB 0.8 GB
Fits Get file →

For 8 GB VRAM, use Q4_K (file size 0.07 GB, memory 0.6 GB) or Q5_0 (0.09 GB, 0.6 GB). If more VRAM is available, Q8_0 (0.12 GB, 0.6 GB) or F16 (0.23 GB, 0.8 GB) can be used for higher precision.

What GPU do you need for stt en fastconformer ctc large?

These figures add the file size, an fp16 KV cache at an 8K context window and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is F16 (0.2 GB file, about 0.8 GB in use).

Which stt en fastconformer ctc large quant should you choose?

Q5_0 (0.1 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

If memory is tight, the smallest file is Q4_K at 0.1 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturecanary-ctc
Parameters116M

Source

Quantized bycstr
FamilyStt
Licensecc-by-4.0
Downloads (HF)2,039
Last updated2026-08-02

Frequently asked questions about stt en fastconformer ctc large

How much VRAM does stt en fastconformer ctc large need?

About 0.6 GB at Q5_0 with an 8K context window. That is the 0.1 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run stt en fastconformer ctc large on an 8 GB GPU?

Yes, with F16: the 0.2 GB file needs about 0.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of stt en fastconformer ctc large GGUF?

It depends on the quant: Q4_K is 0.1 GB, Q5_0 is 0.1 GB, Q8_0 is 0.1 GB, F16 is 0.2 GB.

Where can I download stt en fastconformer ctc large GGUF?

The files are on Hugging Face in the cstr/stt-en-fastconformer-ctc-large-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does stt en fastconformer ctc large use?

Hugging Face lists the license as cc-by-4.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run this model on 8 GB VRAM?

Yes. The Q4_K, Q5_0, and Q8_0 quantisations all estimate 0.6 GB memory at 8k context, well within 8 GB VRAM.

Does this model support multiple languages?

No. The model is English only and transcribes in lower case English alphabet.

What license applies to this model?

The model is distributed under cc‑by‑4.0, the same license as the upstream NVIDIA model.

Similar models

Browse all →

More from cstr

All by cstr →

More Stt models

All Stt →

Other tiny models

All tiny models →