From c2dee5e3c29eba79e591d9e9caebaef15ea4e56b Mon Sep 17 00:00:00 2001
From: hnluo <haoneng.lhn@alibaba-inc.com>
Date: 星期四, 29 六月 2023 11:09:28 +0800
Subject: [PATCH] Merge pull request #687 from alibaba-damo-academy/dev_lhn
---
funasr/utils/wav_utils.py | 4 ++--
1 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/funasr/utils/wav_utils.py b/funasr/utils/wav_utils.py
index e523495..bd067c2 100644
--- a/funasr/utils/wav_utils.py
+++ b/funasr/utils/wav_utils.py
@@ -189,9 +189,9 @@
def wav2num_frame(wav_path, frontend_conf):
try:
- waveform, audio_sr = torchaudio.load(wav_file)
+ waveform, sampling_rate = torchaudio.load(wav_path)
except:
- waveform, audio_sr = soundfile.read(wav_file)
+ waveform, sampling_rate = soundfile.read(wav_path)
waveform = torch.tensor(np.expand_dims(waveform, axis=0))
speech_length = (waveform.shape[1] / sampling_rate) * 1000.
n_frames = (waveform.shape[1] * 1000.0) / (sampling_rate * frontend_conf["frame_shift"] * frontend_conf["lfr_n"])
--
Gitblit v1.9.1