Whisper-large-v2-atcosim_corpus Open-source Speech Recognition Model - Precise Recognition with Low Word Error Rate in Specific Domains

Whisper Large V2 Atcosim Corpus

Developed by daisyyedda

This model is a fine-tuned speech recognition model based on openai/whisper-large-v2, achieving a word error rate of 4.6858 on a specific domain dataset.

Speech Recognition

Transformers

Open Source License:Apache-2.0 #Aviation Communication Speech Recognition #Low Word Error Rate #Multi-GPU Fine-tuning

Downloads 16

Release Time : 5/20/2024

Model Overview

A speech recognition model fine-tuned from Whisper-large-v2, suitable for domain-specific speech-to-text tasks.

Model Features

Low Word Error Rate

Achieved a word error rate of 4.6858 on the evaluation set, demonstrating excellent performance.

Fine-tuned from Whisper-large-v2

Inherits the powerful speech recognition capabilities of Whisper-large-v2 and further optimizes for specific domain data.

Multi-GPU Training

Utilizes multi-GPU distributed training to improve training efficiency.

Model Capabilities

Speech-to-Text

Domain-Specific Speech Recognition

Use Cases

Aviation Communication

Air Traffic Control Communication Transcription

Transcribes communications between air traffic controllers and pilots into text

Word error rate 4.6858

Training Loss	Epoch	Step	Validation Loss	Wer
0.0011	19.2308	250	0.1478	4.8988
0.0001	38.4615	500	0.1606	4.6858

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご

Whisper Large V2 Atcosim Corpus

Model Overview

Model Features

Model Capabilities

Use Cases

🚀 whisper-large-v2-atcosim_corpus

🚀 Quick Start

📚 Documentation

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

📄 License