Model reference · open weights
parakeet-ctc-farsi is an open-weight audio or speech model from Peacockery.
For self-hosting, compare this build's requirements below with the GPU you plan to rent.
Summary of the Peacockery/parakeet-ctc-109m-farsi model card, 2026-10-01
What it is
| Released by | Peacockery |
|---|---|
| Released | 2026-06-10 |
From the model card
A Farsi fine-tune of NVIDIA's Parakeet CTC 109M (the CTC branch of parakeet-tdt_ctc-110m), trained with a custom Farsi SentencePiece tokenizer on 844 hours of quality-classified Farsi speech. It is the best Parakeet-family model from this project; a later variant trained on a stricter 224-hour subset regressed and was retired.
model.nemo: the complete NeMo checkpoint (weights + tokenizer + config)844 hours of Farsi speech: Common Voice, Thomcles, Mana TTS, Neyshekar, FLEURS, WorldSpeech, and Farsi YouTube, with web-scraped portions machine-labeled and filtered by a Scribe quality classifier. Clips capped at 400 characters and 60 chars/sec to drop misaligned transcripts.
Test splits, corpus-level jiwer after shared normalization, re-scored 2026-05-28 (WER %):
| split | WER | CER |
|---|---|---|
| FLEURS | 14.94 | 4.15 |
| Common Voice 25 | 23.19 | 6.27 |
| Mana TTS | 28.53 | 5.07 |
| Neyshekar | 27.87 | 5.48 |
| WorldSpeech | 40.12 | 20.51 |
| YouTube | 34.55 | 13.72 |
For a stronger Farsi model from the same project see Peacockery/omni-ctc-300m-farsi, which wins on every split. This checkpoint is the lighter and faster option (109M parameters, ~350x realtime on the benchmark hardware).
import nemo.collections.asr as nemo_asr
model = nemo_asr.models.EncDecCTCModelBPE.restore_from("model.nemo")
texts = model.transcribe(["audio.wav"])
Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.
How it works