From 47343b5c2f4e1256f60f46d8da0aa2e5de39b6c7 Mon Sep 17 00:00:00 2001
From: 嘉渊 <wangjiaming.wjm@alibaba-inc.com>
Date: 星期六, 05 八月 2023 17:53:08 +0800
Subject: [PATCH] init repo
---
funasr/utils/prepare_data.py | 21 ++++++++++++++-------
1 files changed, 14 insertions(+), 7 deletions(-)
diff --git a/funasr/utils/prepare_data.py b/funasr/utils/prepare_data.py
index f61e501..8d82a2f 100644
--- a/funasr/utils/prepare_data.py
+++ b/funasr/utils/prepare_data.py
@@ -7,6 +7,7 @@
import numpy as np
import torch.distributed as dist
import torchaudio
+import soundfile
def filter_wav_text(data_dir, dataset):
@@ -42,7 +43,11 @@
def wav2num_frame(wav_path, frontend_conf):
- waveform, sampling_rate = torchaudio.load(wav_path)
+ try:
+ waveform, sampling_rate = torchaudio.load(wav_path)
+ except:
+ waveform, sampling_rate = soundfile.read(wav_path)
+ waveform = np.expand_dims(waveform, axis=0)
n_frames = (waveform.shape[1] * 1000.0) / (sampling_rate * frontend_conf["frame_shift"] * frontend_conf["lfr_n"])
feature_dim = frontend_conf["n_mels"] * frontend_conf["lfr_m"]
return n_frames, feature_dim
@@ -185,18 +190,22 @@
for i in range(nj):
path = ""
for file_name in file_names:
- path = path + os.path.join(split_path, str(i + 1), file_name)
+ path = path + " " + os.path.join(split_path, str(i + 1), file_name)
f_data.write(path + "\n")
def prepare_data(args, distributed_option):
distributed = distributed_option.distributed
+ 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"]
if not distributed or distributed_option.dist_rank == 0:
if hasattr(args, "filter_input") and args.filter_input:
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)
@@ -204,13 +213,11 @@
generate_data_list(args, args.data_dir, args.train_set)
generate_data_list(args, args.data_dir, args.valid_set)
- 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(",")
+ 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":
args.train_shape_file = [os.path.join(args.data_dir, args.train_set, "{}_shape".format(data_names[0]))]
- args.valid_shape_file = [os.path.join(args.data_dir, args.valid_set, "{}}_shape".format(data_names[0]))]
+ args.valid_shape_file = [os.path.join(args.data_dir, args.valid_set, "{}_shape".format(data_names[0]))]
args.train_data_path_and_name_and_type, args.valid_data_path_and_name_and_type = [], []
for file_name, data_name, data_type in zip(file_names, data_names, data_types):
args.train_data_path_and_name_and_type.append(
--
Gitblit v1.9.1