From 580b11b57ac4b62f7e2acda73813a4e10e8e4cd3 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期二, 10 十月 2023 17:17:29 +0800
Subject: [PATCH] v0.8.0
---
egs_modelscope/asr/TEMPLATE/README.md | 4 ++--
1 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/egs_modelscope/asr/TEMPLATE/README.md b/egs_modelscope/asr/TEMPLATE/README.md
index ef724b5..bd0e6a9 100644
--- a/egs_modelscope/asr/TEMPLATE/README.md
+++ b/egs_modelscope/asr/TEMPLATE/README.md
@@ -34,7 +34,7 @@
import soundfile
speech, sample_rate = soundfile.read("example/asr_example.wav")
-chunk_size = [0, 10, 5] #[5, 10, 5] 600ms, [8, 8, 4] 480ms
+chunk_size = [0, 10, 5] #[0, 10, 5] 600ms, [0, 8, 4] 480ms
encoder_chunk_look_back = 4 #number of chunks to lookback for encoder self-attention
decoder_chunk_look_back = 1 #number of encoder chunks to lookback for decoder cross-attention
param_dict = {"cache": dict(), "is_final": False, "chunk_size": chunk_size,
@@ -202,7 +202,7 @@
if __name__ == '__main__':
params = modelscope_args(model="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch", data_path="./data")
params.output_dir = "./checkpoint" # m妯″瀷淇濆瓨璺緞
- params.data_path = "./example_data/" # 鏁版嵁璺緞
+ params.data_path = "speech_asr_aishell1_trainsets" # 鏁版嵁璺緞
params.dataset_type = "small" # 灏忔暟鎹噺璁剧疆small锛岃嫢鏁版嵁閲忓ぇ浜�1000灏忔椂锛岃浣跨敤large
params.batch_bins = 2000 # batch size锛屽鏋渄ataset_type="small"锛宐atch_bins鍗曚綅涓篺bank鐗瑰緛甯ф暟锛屽鏋渄ataset_type="large"锛宐atch_bins鍗曚綅涓烘绉掞紝
params.max_epoch = 20 # 鏈�澶ц缁冭疆鏁�
--
Gitblit v1.9.1