From fa74e1ebc68c77f81c238e7107b658dfaa5ee5f9 Mon Sep 17 00:00:00 2001
From: zxcd <228587199@qq.com>
Date: Fri, 27 Sep 2024 03:41:07 +0000
Subject: [PATCH] fix

---
 README.md                                     | 2 +-
 paddlespeech/cls/exps/panns/deploy/predict.py | 7 +++++--
 2 files changed, 6 insertions(+), 3 deletions(-)

diff --git a/README.md b/README.md
index 19ec61cb0..5197ff4c7 100644
--- a/README.md
+++ b/README.md
@@ -7,7 +7,7 @@
     <a href="./LICENSE"><img src="https://img.shields.io/badge/license-Apache%202-red.svg"></a>
     <a href="https://github.com/PaddlePaddle/PaddleSpeech/releases"><img src="https://img.shields.io/github/v/release/PaddlePaddle/PaddleSpeech?color=ffa"></a>
     <a href="support os"><img src="https://img.shields.io/badge/os-linux%2C%20win%2C%20mac-pink.svg"></a>
-    <a href=""><img src="https://img.shields.io/badge/python-3.7+-aff.svg"></a>
+    <a href=""><img src="https://img.shields.io/badge/python-3.8+-aff.svg"></a>
     <a href="https://github.com/PaddlePaddle/PaddleSpeech/graphs/contributors"><img src="https://img.shields.io/github/contributors/PaddlePaddle/PaddleSpeech?color=9ea"></a>
     <a href="https://github.com/PaddlePaddle/PaddleSpeech/commits"><img src="https://img.shields.io/github/commit-activity/m/PaddlePaddle/PaddleSpeech?color=3af"></a>
     <a href="https://github.com/PaddlePaddle/PaddleSpeech/issues"><img src="https://img.shields.io/github/issues/PaddlePaddle/PaddleSpeech?color=9cc"></a>
diff --git a/paddlespeech/cls/exps/panns/deploy/predict.py b/paddlespeech/cls/exps/panns/deploy/predict.py
index f14b44215..866a669e8 100644
--- a/paddlespeech/cls/exps/panns/deploy/predict.py
+++ b/paddlespeech/cls/exps/panns/deploy/predict.py
@@ -17,7 +17,7 @@ import os
 import numpy as np
 from paddle import inference
 from paddle.audio.datasets import ESC50
-from paddle.audio.features import MelSpectrogram
+from paddle.audio.features import LogMelSpectrogram
 from paddleaudio.backends import soundfile_load as load_audio
 from scipy.special import softmax
 
@@ -53,7 +53,10 @@ def extract_features(files: str, **kwargs):
             pad_width = max_length - len(waveforms[i])
             waveforms[i] = np.pad(waveforms[i], pad_width=(0, pad_width))
 
-        feat = MelSpectrogram(waveforms[i], sr, **kwargs).transpose()
+        feature_extractor = LogMelSpectrogram(sr, **kwargs)
+        feat = feature_extractor(paddle.to_tensor(waveforms[i]))
+        feat = paddle.transpose(feat, perm=[1, 0]).unsqueeze(0)
+
         feats.append(feat)
 
     return np.stack(feats, axis=0)