AxForge
Sign in Get started

Model reference · open weights

Shenava-Koochik

Available as managed deployment Audio Reza2kn · community Speech→text 1 variants 746 dl/mo

Shenava-Koochik is an open-weight audio or speech model from Reza2kn. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.

Request deployment All audio & music

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

What it is

Released byReza2kn
TypeAudio & music
TaskSpeech→text
Runs withnemo
Released2026-07-04
Popularity746 downloads / month
LicenceOpen weights

About

What Shenava-Koochik is

Persian (Farsi) ASR — FastConformer hybrid RNNT + CTC (114M). The both-heads successor to v1.0.

Read the full model card

What is new

  • RNNT head revived. v1.0's RNNT head was broken (a tokenizer/blank misalignment made greedy decoding loop forever, ~4398% WER). v1.5 surgically re-initializes the RNNT prednet+joint under the ve_tok_v4 tokenizer and trains it up via a 2-phase curriculum -> a working transducer head.
  • CTC head preserved. The deployed, record-setting CTC head is kept identical to v1.0 (encoder frozen during the corrective RNNT finetune) -> zero CTC regression.

Benchmarks (golden-6669, strict fair_text normalizer, att_context [70,13])

headv1.0v1.5
CTC8.12%8.12% (identical)
RNNT4398% (broken)9.50%

CTC remains the recommended/deployed head; RNNT is newly functional. Character error rate ~2.6%.

Usage

from nemo.collections.asr.models import ASRModel
m = ASRModel.from_pretrained("Reza2kn/Shenava-Koochik-v1.5")
m.change_decoding_strategy(decoder_type="ctc")   # or "rnnt"
print(m.transcribe(["audio.wav"]))

Notes

  • RNNT output leans colloquial (trained on audio-faithful ASR labels).
  • Trained on a cleaned mix (pseudo corpus + synthetic hardwords + human/article gold) with benchmark de-duplication and label-quality filtering (over-extension / repetition-loop removal).

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 shenava-koochik for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (shenava-koochik 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="shenava-koochik" -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.

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