# Automatic Speech Recognition (ASR) — Data

来源：https://www.kaggle.com/competitions/automatic-speech-recognition-s24/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

The dataset is given in a similar format to previous homework in this course.

## Subdirectories

*   **train-clean-50** - the training set
*   **train-clean-100** - the training set
*   **dev-clean** - the training set
*   **test-clean** - the training set

## Files

*   `encoder_weights.pth` - reference CNN-LSTM encoder weights