From 9b4e9cc8a0311e5243d69b73ed073e7ea441982e Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期三, 27 三月 2024 16:05:29 +0800
Subject: [PATCH] train update

---
 examples/aishell/branchformer/conf/branchformer_12e_6d_2048_256.yaml |    5 ++---
 1 files changed, 2 insertions(+), 3 deletions(-)

diff --git a/examples/aishell/branchformer/conf/branchformer_12e_6d_2048_256.yaml b/examples/aishell/branchformer/conf/branchformer_12e_6d_2048_256.yaml
index d6caf5d..e14b6af 100644
--- a/examples/aishell/branchformer/conf/branchformer_12e_6d_2048_256.yaml
+++ b/examples/aishell/branchformer/conf/branchformer_12e_6d_2048_256.yaml
@@ -94,9 +94,9 @@
 dataset: AudioDataset
 dataset_conf:
     index_ds: IndexDSJsonl
-    batch_sampler: RankFullLocalShuffleBatchSampler
+    batch_sampler: BatchSampler
     batch_type: example # example or length
-    batch_size: 32 # if batch_type is example, batch_size is the numbers of samples; if length, batch_size is source_token_len+target_token_len;
+    batch_size: 16 # if batch_type is example, batch_size is the numbers of samples; if length, batch_size is source_token_len+target_token_len;
     max_token_length: 2048 # filter samples if source_token_len+target_token_len > max_token_length,
     buffer_size: 1024
     shuffle: True
@@ -108,7 +108,6 @@
 tokenizer: CharTokenizer
 tokenizer_conf:
   unk_symbol: <unk>
-  split_with_space: true
 
 
 ctc_conf:

--
Gitblit v1.9.1