S

Sew D Small 100k Timit

Developed by patrickvonplaten
This model is an automatic speech recognition model fine-tuned from asapp/sew-d-small-100k on the TIMIT_ASR - NA dataset, achieving a word error rate of 0.8061 on the evaluation set.
Downloads 16
Release Time : 3/2/2022

Model Overview

This is a model for automatic speech recognition (ASR), specifically optimized for the TIMIT_ASR dataset.

Model Features

Efficient fine-tuning
Fine-tuned on the TIMIT_ASR dataset based on the pre-trained sew-d-small-100k model
Optimized performance
Achieved a word error rate of 0.8061 on the TIMIT_ASR evaluation set
Lightweight
Small version model, suitable for resource-constrained environments

Model Capabilities

English speech recognition
Speech-to-text

Use Cases

Speech technology
Speech transcription
Convert English speech to text
Word error rate 0.8061
Voice command recognition
Recognize voice commands and convert them into executable commands
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase