Skip to content

ASR Benchmark

Jackwaterveg edited this page May 24, 2022 · 23 revisions

ASR Benchmark

RTF 定义

RTF = 处理语音总时长 / 语音总时长

测试数据

Aishell-1 test 集作为测试集。

TODO:数据分布。

Non-Streaming ASR

机器硬件:GPU V100 32 G, CPU:Intel(R) Xeon(R) Gold 6271C CPU @ 2.60GHz
测试脚本: CLI

Acoustic Model dedoding_method ctc_weight decoding_chunk_size num_decoding_left_chunk RTF
conformer_aishell attention_rescoring 0.5 16 -1 0.0665

Streaming ASR

机器硬件:GPU V100 32 G, CPU:Intel(R) Xeon(R) Gold 6271C CPU @ 2.60GHz
测试脚本:流式服务

Acoustic Model dedoding_method ctc_weight decoding_chunk_size num_decoding_left_chunk RTF
conformer_aishell attention_rescoring 0.5 16 -1 0.250782
Clone this wiki locally