From 54931dd4e1a099d7d6f144c4e12e5453deb3aa26 Mon Sep 17 00:00:00 2001
From: 雾聪 <wucong.lyb@alibaba-inc.com>
Date: 星期三, 28 六月 2023 10:41:57 +0800
Subject: [PATCH] Merge branch 'main' of https://github.com/alibaba-damo-academy/FunASR into main
---
funasr/utils/prepare_data.py | 9 +++++++--
1 files changed, 7 insertions(+), 2 deletions(-)
diff --git a/funasr/utils/prepare_data.py b/funasr/utils/prepare_data.py
index 36795b4..0e773bb 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
@@ -185,7 +190,7 @@
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")
--
Gitblit v1.9.1