---
license: mit
datasets:
- jacktol/ATC-ASR-Dataset
language:
- en
metrics:
- wer
base_model:
- nvidia/parakeet-tdt-0.6b-v3
pipeline_tag: automatic-speech-recognition
library_name: nemo
tags:
- parakeet
- atc
- nemo
---

# Parakeet-TDT-0.6B-v3 Fine-Tuned on ATC-ASR Dataset

## Overview

This repository contains a fine-tuned version of **[NVIDIA Parakeet-TDT-0.6B-v3](https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3)**, optimized for automatic speech recognition (ASR) in air traffic control (ATC) communications.  
The model was fine-tuned using **NVIDIA NeMo** on the **[Jacktol ATC-ASR Dataset](https://huggingface.co/datasets/jacktol/ATC-ASR-Dataset)** to improve recognition accuracy in noisy, domain-specific ATC environments.  
Following fine-tuning, the model achieves a **state-of-the-art word error rate (WER) of 0.0599** on the dataset’s official test split.

---

## Results

| Metric                               | Value                                      |
| ------------------------------------ | ------------------------------------------ |
| **Validation Word Error Rate (WER)** | **0.0558**                                 |
| **Test Word Error Rate (WER)**       | **0.0599**                                 |
| **Training Time**                    | < 1 hour on NVIDIA H200                    |
| **Framework**                        | NVIDIA NeMo                                |
| **Checkpoint Size**                  | 2.34 GB                                    |

---

## Model Details

| Attribute | Description |
|------------|--------------|
| **Base Model** | `nvidia/parakeet-tdt-0.6b-v3` |
| **Dataset** | [`jacktol/ATC-ASR-Dataset`](https://huggingface.co/datasets/jacktol/ATC-ASR-Dataset) |
| **Framework** | [NVIDIA NeMo](https://github.com/NVIDIA/NeMo) |
| **Epochs** | 16 |
| **Batch Size** | 16 |
| **Learning Rate** | 1e-4 |
| **Optimizer** | AdamW (weight decay 1e-3) |
| **Scheduler** | CosineAnnealing |
| **Warmup Steps** | 5000 |
| **Min LR** | 5e-6 |
| **Precision** | Mixed precision (FP16) |
| **Tokenizer** | Parakeet default subword tokenizer |

---

## Dataset

- **Name:** [Jacktol ATC-ASR Dataset](https://huggingface.co/datasets/jacktol/ATC-ASR-Dataset)  
- **Domain:** Air Traffic Control communications  
- **Language:** English  
- **Sampling Rate:** 16 kHz  
- **Format:** WAV + JSON transcripts  

---

## Citation

If you use this model, please cite both the base model and dataset authors:

```bibtex
@misc{nvidia2024parakeet,
  title={Parakeet-TDT-0.6B-v3},
  author={NVIDIA},
  year={2024},
  publisher={Hugging Face},
  howpublished={\url{https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3}}
}

@dataset{jacktol_atc_asr,
  title={ATC-ASR Dataset},
  author={Jacktol},
  year={2023},
  howpublished={\url{https://huggingface.co/datasets/jacktol/ATC-ASR-Dataset}}
}
```