---
license: cc-by-4.0
library_name: coreai
pipeline_tag: automatic-speech-recognition
base_model: nvidia/parakeet-tdt-0.6b-v3
tags: [core-ai, coreaikit, parakeet, tdt, rnn-t, transducer, asr, on-device, apple]
---

# Parakeet-TDT-0.6B — Core AI

[`nvidia/parakeet-tdt-0.6b-v3`](https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3) (cc-by-4.0, 600M)
converted to **Apple Core AI** `.aimodel` — the first **transducer / TDT (RNN-T family)** ASR in the
[zoo](https://github.com/john-rocky/coreai-models-community). Transcribes ≤~29 s clips in 25
European languages as **three stateless graphs + a host greedy loop** (no LLM runtime).

- `parakeet_encoder_float16_L2885.aimodel` — FastConformer encoder + projector (fp16, ~1.2 GB),
  `mel[1,128,2885] → enc_proj[1,361,640]`.
- `parakeet_predict_float32.aimodel` — embedding → 2-layer LSTM → projector (fp32),
  `token[1,1],h,c[2,1,640] → dec_out[1,640],h',c'`.
- `parakeet_joint_float32.aimodel` — `head(relu(enc_frame+dec_out))` (fp32),
  `→ token_logits[1,8193], dur_logits[1,5]`.
- `tokenizer.json` (+ `tokenizer_config.json`), `mel_filters_128x257_f32.bin` (librosa-slaney).

Gated **77/77 token-exact** end-to-end vs the HF `ParakeetForTDT` reference, and again token-exact
through the Swift **CoreAIKit** `KitParakeetModel`. blank 8192 · durations [0,1,2,3,4] · 16 kHz.

## Use (CoreAIKit)

```swift
let parakeet = try await KitParakeetModel(model: .parakeetTDT)
let result = try await parakeet.transcribe(samples: pcm16kMono)   // 16 kHz mono Float
```