From b57b98364ff60ae0119b2e8d92471316bb4e504f Mon Sep 17 00:00:00 2001
From: zhifu gao <zhifu.gzf@alibaba-inc.com>
Date: 星期三, 22 十一月 2023 00:36:35 +0800
Subject: [PATCH] funasr v2 setup (#1106)
---
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