Model reference · open weights

stt_ar_fastconformer_hybrid_large_pcd-mirror

Available as managed deployment Audio dev-ahmedhany · community Speech→text 1 variants 689 dl/mo

stt_ar_fastconformer_hybrid_large_pcd-mirror is an open-weight audio or speech model from dev-ahmedhany. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.

Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.

What it is

Released bydev-ahmedhany
TypeAudio & music
TaskSpeech→text
Runs withnemo
Released2026-05-05
Popularity689 downloads / month
LicenceOpen weights

About

What stt_ar_fastconformer_hybrid_large_pcd-mirror is

This is a byte-exact mirror of NVIDIAs Arabic FastConformer hybrid Transducer-CTC model with Punctuation, Capitalization, and Diacritics output (Tashkeel).

Read the full model card

Why a mirror

This mirror exists for availability redundancy in case the upstream repo is renamed, gated, or removed. It is byte-identical to the upstream checkpoint and carries no modifications.

Source

File integrity

sha256sum stt_ar_fastconformer_hybrid_large_pcd_v1.0.nemo
d29d19d7c054a5fc010ac6815e9cbb0dd1b21a30e0a7f7f2982e1fecaf0c3e31  stt_ar_fastconformer_hybrid_large_pcd_v1.0.nemo

Verify after download:

huggingface-cli download dev-ahmedhany/stt_ar_fastconformer_hybrid_large_pcd_v1.0-mirror \
  stt_ar_fastconformer_hybrid_large_pcd_v1.0.nemo --local-dir .
sha256sum stt_ar_fastconformer_hybrid_large_pcd_v1.0.nemo
# expected: d29d19d7c054a5fc010ac6815e9cbb0dd1b21a30e0a7f7f2982e1fecaf0c3e31

Attribution (CC-BY-4.0 requirement)

Original model and weights by NVIDIA. All credit for the model architecture, training, and weights belongs to NVIDIA. This mirror simply preserves bit-for-bit access to the upstream artifact.

If you use this model, please cite the original NeMo / FastConformer papers as listed on the upstream model card.

Usage

Identical to upstream:

import nemo.collections.asr as nemo_asr
m = nemo_asr.models.EncDecHybridRNNTCTCBPEModel.from_pretrained(
    "dev-ahmedhany/stt_ar_fastconformer_hybrid_large_pcd_v1.0-mirror"
)
print(m.transcribe(["audio.wav"])[0].text)

For complete usage details, training data, evaluation WER per dataset, and limitations, see the upstream model card linked above.

License

This mirror is distributed under CC-BY-4.0, the same license as the upstream NVIDIA repository. You may use, redistribute, and modify under the terms of CC-BY-4.0 with proper attribution to NVIDIA.

From the published model card. Full card on the HuggingFace links in the sidebar.

How it works

How audio & music work

Audio or textinputAudio modelrecognise / synthesiseText or audiooutputSpeech-to-text turns audio into text; text-to-speech and music models turn text into audio.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys stt-ar-fastconformer-hybrid-large-pcd-mirror for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (stt-ar-fastconformer-hybrid-large-pcd-mirror 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="stt-ar-fastconformer-hybrid-large-pcd-mirror" -F file=@audio.mp3

Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms