From c568628130ac42ebeea8cf48fe926520a31ff511 Mon Sep 17 00:00:00 2001
From: 嘉渊 <wangjiaming.wjm@alibaba-inc.com>
Date: 星期二, 16 五月 2023 10:57:21 +0800
Subject: [PATCH] update repo
---
funasr/utils/prepare_data.py | 28 ++++++++++++++++++++++++----
1 files changed, 24 insertions(+), 4 deletions(-)
diff --git a/funasr/utils/prepare_data.py b/funasr/utils/prepare_data.py
index e095a4c..f976a03 100644
--- a/funasr/utils/prepare_data.py
+++ b/funasr/utils/prepare_data.py
@@ -27,7 +27,7 @@
parts = line.strip().split()
if len(parts) < 2:
continue
- text_dict[parts[0]] = " ".join(parts[1:]).lower()
+ text_dict[parts[0]] = " ".join(parts[1:])
filter_count = 0
with open(wav_file, "w") as f_wav, open(text_file, "w") as f_text:
for sample_name, wav_path in wav_dict.items():
@@ -70,7 +70,7 @@
f.flush()
-def calc_shape(args, dataset, nj=32):
+def calc_shape(args, dataset, nj=64):
shape_path = os.path.join(args.data_dir, dataset, "speech_shape")
if os.path.exists(shape_path):
logging.info('Shape file for small dataset already exists.')
@@ -90,7 +90,7 @@
start = 0
for i in range(nj):
end = start + num_job_lines
- file = os.path.join(shape_path, "wav.scp.{}".format(str(i + 1)))
+ file = os.path.join(split_shape_path, "wav.scp.{}".format(str(i + 1)))
with open(file, "w") as f:
if i == nj - 1:
f.writelines(lines[start:])
@@ -115,7 +115,7 @@
logging.info('Generating shape files done.')
-def generate_data_list(data_dir, dataset, nj=32):
+def generate_data_list(data_dir, dataset, nj=64):
list_file = os.path.join(data_dir, dataset, "data.list")
if os.path.exists(list_file):
logging.info('Data list for large dataset already exists.')
@@ -181,8 +181,28 @@
["{}/{}/wav.scp".format(args.data_dir, args.valid_set), data_names[0], data_types[0]],
["{}/{}/text".format(args.data_dir, args.valid_set), data_names[1], data_types[1]]
]
+ if args.embed_path is not None:
+ args.train_data_path_and_name_and_type.append(
+ [os.path.join(args.embed_path, "embeds", args.train_set, "embeds.scp"), "embed", "kaldi_ark"])
+ args.valid_data_path_and_name_and_type.append(
+ [os.path.join(args.embed_path, "embeds", args.valid_set, "embeds.scp"), "embed", "kaldi_ark"])
else:
args.train_data_file = os.path.join(args.data_dir, args.train_set, "data.list")
args.valid_data_file = os.path.join(args.data_dir, args.valid_set, "data.list")
+ if args.embed_path is not None:
+ for d in [args.train_set, args.valid_set]:
+ file = os.path.join(args.data_dir, d, "data.list")
+ with open(file) as f:
+ lines = f.readlines()
+ out_file = os.path.join(args.data_dir, d, "data_with_embed.list")
+ with open(out_file, "w") as out_f:
+ for line in lines:
+ parts = line.strip().split()
+ idx = parts[0].split("/")[-2]
+ embed_file = os.path.join(args.embed_path, "embeds", args.valid_set, "ark",
+ "embeds.{}.ark".format(idx))
+ out_f.write(parts[0] + " " + parts[1] + " " + embed_file + "\n")
+ args.train_data_file = os.path.join(args.data_dir, args.train_set, "data_with_embed.list")
+ args.valid_data_file = os.path.join(args.data_dir, args.valid_set, "data_with_embed.list")
if distributed:
dist.barrier()
--
Gitblit v1.9.1