From adc88bd9e76644badbbe006913addfa7cbe5d89c Mon Sep 17 00:00:00 2001
From: shixian.shi <shixian.shi@alibaba-inc.com>
Date: 星期四, 23 十一月 2023 20:40:15 +0800
Subject: [PATCH] Merge remote-tracking branch 'refs/remotes/origin/main' update contextual forward
---
funasr/utils/prepare_data.py | 4 ++--
1 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/funasr/utils/prepare_data.py b/funasr/utils/prepare_data.py
index 702c7f3..36eebdc 100644
--- a/funasr/utils/prepare_data.py
+++ b/funasr/utils/prepare_data.py
@@ -5,7 +5,7 @@
import kaldiio
import numpy as np
-import soundfile
+import librosa
import torch.distributed as dist
import torchaudio
@@ -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"]
--
Gitblit v1.9.1