From e24dbdc496debec225414d4d2c760f5775e64f2a Mon Sep 17 00:00:00 2001
From: 天地 <tiandiweizun@gmail.com>
Date: 星期三, 26 三月 2025 13:44:41 +0800
Subject: [PATCH] 感觉应该从文件读取更合适，因为上面判断了文件存在，且可以读取，如果本身是文本的话，下面也会有逻辑进行处理 (#2452)
---
funasr/models/paraformer/template.yaml | 4 ++--
1 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/funasr/models/paraformer/template.yaml b/funasr/models/paraformer/template.yaml
index bccf638..249e88c 100644
--- a/funasr/models/paraformer/template.yaml
+++ b/funasr/models/paraformer/template.yaml
@@ -87,7 +87,7 @@
grad_clip: 5
max_epoch: 150
keep_nbest_models: 10
- avg_nbest_model: 5
+ avg_nbest_model: 10
log_interval: 50
optim: adam
@@ -100,7 +100,7 @@
dataset: AudioDataset
dataset_conf:
index_ds: IndexDSJsonl
- batch_sampler: DynamicBatchLocalShuffleSampler
+ batch_sampler: BatchSampler
batch_type: example # example or length
batch_size: 1 # 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,
--
Gitblit v1.9.1