From 4ace5a95b052d338947fc88809a440ccd55cf6b4 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期四, 16 十一月 2023 16:39:52 +0800
Subject: [PATCH] funasr pages
---
funasr/utils/prepare_data.py | 6 ++++--
1 files changed, 4 insertions(+), 2 deletions(-)
diff --git a/funasr/utils/prepare_data.py b/funasr/utils/prepare_data.py
index 3ae18b8..702c7f3 100644
--- a/funasr/utils/prepare_data.py
+++ b/funasr/utils/prepare_data.py
@@ -5,9 +5,9 @@
import kaldiio
import numpy as np
+import soundfile
import torch.distributed as dist
import torchaudio
-import soundfile
def filter_wav_text(data_dir, dataset):
@@ -87,6 +87,7 @@
sample_name, feature_path = line.strip().split()
feature = kaldiio.load_mat(feature_path)
n_frames, feature_dim = feature.shape
+ write_flag = True
if n_frames > 0 and length_min > 0:
write_flag = n_frames >= length_min
if n_frames > 0 and length_max > 0:
@@ -198,6 +199,7 @@
data_names = args.dataset_conf.get("data_names", "speech,text").split(",")
data_types = args.dataset_conf.get("data_types", "sound,text").split(",")
file_names = args.data_file_names.split(",")
+ batch_type = args.dataset_conf["batch_conf"]["batch_type"]
print("data_names: {}, data_types: {}, file_names: {}".format(data_names, data_types, file_names))
assert len(data_names) == len(data_types) == len(file_names)
if args.dataset_type == "small":
@@ -228,7 +230,7 @@
filter_wav_text(args.data_dir, args.train_set)
filter_wav_text(args.data_dir, args.valid_set)
- if args.dataset_type == "small":
+ if args.dataset_type == "small" and batch_type != "unsorted":
calc_shape(args, args.train_set)
calc_shape(args, args.valid_set)
--
Gitblit v1.9.1