20 lines
470 B
Markdown

# Introduction
This recipe includes scripts for training Zipformer model using both English and Chinese datasets.
# Included Training Sets
1. LibriSpeech (English)
2. AiShell-2 (Chinese)
3. TAL-CSASR (Code-Switching, Chinese and English)
|Datset| Number of hours| URL|
|---|---:|---|
|**TOTAL**|2,547|---|
|LibriSpeech|960|https://www.openslr.org/12/|
|AiShell-2|1,000|http://www.aishelltech.com/aishell_2|
|TAL-CSASR|587|https://ai.100tal.com/openData/voice|