From 8c7b7e5feb68fda1fc4ddd627bad0f915358149e Mon Sep 17 00:00:00 2001
From: Zhanzhao (Deo) Liang <liangzhanzhao1985@gmail.com>
Date: 星期三, 25 十二月 2024 16:40:29 +0800
Subject: [PATCH] fix export_meta import of sense voice (#2334)
---
funasr/models/seaco_paraformer/template.yaml | 15 ++++++++++-----
1 files changed, 10 insertions(+), 5 deletions(-)
diff --git a/funasr/models/seaco_paraformer/template.yaml b/funasr/models/seaco_paraformer/template.yaml
index 52654ac..2bf0825 100644
--- a/funasr/models/seaco_paraformer/template.yaml
+++ b/funasr/models/seaco_paraformer/template.yaml
@@ -36,7 +36,7 @@
pos_enc_class: SinusoidalPositionEncoder
normalize_before: true
kernel_size: 11
- sanm_shfit: 0
+ sanm_shift: 0
selfattention_layer_type: sanm
# decoder
@@ -51,7 +51,7 @@
src_attention_dropout_rate: 0.1
att_layer_num: 16
kernel_size: 11
- sanm_shfit: 0
+ sanm_shift: 0
# seaco decoder
seaco_decoder: ParaformerSANMDecoder
@@ -64,17 +64,22 @@
self_attention_dropout_rate: 0.1
src_attention_dropout_rate: 0.1
kernel_size: 21
- sanm_shfit: 0
+ sanm_shift: 0
use_output_layer: false
wo_input_layer: true
-predictor: CifPredictorV2
+predictor: CifPredictorV3
predictor_conf:
idim: 512
threshold: 1.0
l_order: 1
r_order: 1
tail_threshold: 0.45
+ smooth_factor2: 0.25
+ noise_threshold2: 0.01
+ upsample_times: 3
+ use_cif1_cnn: false
+ upsample_type: cnn_blstm
# frontend related
frontend: WavFrontend
@@ -129,7 +134,7 @@
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