From 2acd24f0158b2c86d2fb4e6f1134b67a1150500e Mon Sep 17 00:00:00 2001
From: jmwang66 <wangjiaming.wjm@alibaba-inc.com>
Date: 星期四, 29 二月 2024 17:14:59 +0800
Subject: [PATCH] update whisper lid (#1407)
---
funasr/utils/prepare_data.py | 5 +++--
1 files changed, 3 insertions(+), 2 deletions(-)
diff --git a/funasr/utils/prepare_data.py b/funasr/utils/prepare_data.py
index c9615e7..36eebdc 100644
--- a/funasr/utils/prepare_data.py
+++ b/funasr/utils/prepare_data.py
@@ -5,9 +5,9 @@
import kaldiio
import numpy as np
+import librosa
import torch.distributed as dist
import torchaudio
-import soundfile
def filter_wav_text(data_dir, dataset):
@@ -46,7 +46,7 @@
try:
waveform, sampling_rate = torchaudio.load(wav_path)
except:
- waveform, sampling_rate = soundfile.read(wav_path)
+ waveform, sampling_rate = librosa.load(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"]
@@ -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:
--
Gitblit v1.9.1