AbijahKaj/parakeet-rnnt-120m-web

Parakeet RNNT 120M — Web/SafeTensors Export

Browser-optimized SafeTensors export of nvidia/parakeet_realtime_eou_120m-v1.

Model Details

Property	Value
Base model	nvidia/parakeet_realtime_eou_120m-v1
Architecture	FastConformer-RNNT (17 layers, d_model=512)
Parameters	~120M
Decoder	RNN-Transducer (RNNT) — streaming-optimized
Language	English
Weights format	SafeTensors, float16 (~220 MB)
Vocab size	1027 tokens (SentencePiece BPE)
Mel bands	128
Context	Limited attention context [70, 1] — streaming-friendly

Files

• model.safetensors — all weights in float16
• model_config.json — architecture hyperparameters
• vocab.json — token ID → text mapping

Usage with audio-ml

const base = 'https://huggingface.co/AbijahKaj/parakeet-rnnt-120m-web/resolve/main';
const config = await fetch(`${base}/model_config.json`).then(r => r.text());
const vocab = await fetch(`${base}/vocab.json`).then(r => r.text());
const weights = await fetch(`${base}/model.safetensors`).then(r => r.arrayBuffer());
await recognizer.loadFromBuffers(weights, config, vocab);

Export Process

Converted from the original NeMo checkpoint using:

python tools/export_nemo_to_safetensors.py \
    --model nvidia/parakeet_realtime_eou_120m-v1 \
    --output-dir exported/parakeet-rnnt-120m

Attribution

This is a format conversion (NeMo → SafeTensors fp16) of NVIDIA's original model. No fine-tuning or weight modification was performed. All credit for the model architecture and training goes to NVIDIA. See the original model card for full details, benchmarks, and license terms.

License: CC-BY-4.0 (inherited from the original model)