Whisper Large v3 Fine-Tuned for Air Traffic Control (ATC)
task
dataset
metrics
type
automatic-speech-recognition
name
type
ATC ASR Dataset
jacktol/ATC-ASR-Dataset
name
type
value
Word Error Rate (WER)
wer
6.5
Model Overview
This model is a fine-tuned version of OpenAI's Whisper Large v3 model, specifically trained on Air Traffic Control (ATC) communication datasets. The fine-tuning process significantly improves transcription accuracy on domain-specific aviation communications, achieving a Word Error Rate (WER) of 6.5% on the test set. The model is particularly effective at handling accent variations and ambiguous phrasing often encountered in ATC communications.
Base Model: OpenAI Large v3
Fine-tuned Model WER: 6.5%
Model Description
This fine-tuned model is optimized to handle short, distinct transmissions between pilots and air traffic controllers. It is fine-tuned using data from:
The fine-tuned model demonstrates enhanced performance in interpreting various accents, recognizing non-standard phraseology, and processing noisy or distorted communications. It is highly suitable for aviation-related transcription tasks.
Intended Use
The fine-tuned Whisper model is designed for:
Transcribing aviation communication: Providing accurate transcriptions for ATC communications, including accents and variations in English phrasing.
Air Traffic Control Systems: Assisting in real-time transcription of pilot-ATC conversations, helping improve situational awareness.
Research and training: Useful for researchers, developers, or aviation professionals studying ATC communication or developing new tools for aviation safety.
Training Procedure
Hardware: Fine-tuning was conducted on two H100 SXM5 GPUs with 80GB VRAM.
Epochs: 3.25
Learning Rate: 1e-5
Batch Size: 10 with no gradient accumulation
Augmentation: Offline data augmentation techniques were utilized in the training set (Gaussian noise, pitch shifting, etc.).
Evaluation Metric: Word Error Rate (WER)
Limitations
While the fine-tuned model performs well in ATC-specific communications, it may not generalize as effectively to other domains of speech. Additionally, like most speech-to-text models, transcription accuracy can be affected by extremely poor-quality audio or heavily accented speech not encountered or properly represented during training.
