From 5fec3c9e58fceda85fa2daf7deec2492372dac8a Mon Sep 17 00:00:00 2001
From: Chong Zhang <iriszhangchong@gmail.com>
Date: 星期二, 23 五月 2023 17:01:47 +0800
Subject: [PATCH] Update modelscope_models.md
---
funasr/fileio/sound_scp.py | 21 +++++++++++++++++++--
1 files changed, 19 insertions(+), 2 deletions(-)
diff --git a/funasr/fileio/sound_scp.py b/funasr/fileio/sound_scp.py
index dc872b0..c752fe6 100644
--- a/funasr/fileio/sound_scp.py
+++ b/funasr/fileio/sound_scp.py
@@ -2,10 +2,14 @@
from pathlib import Path
from typing import Union
+import random
import numpy as np
import soundfile
import librosa
from typeguard import check_argument_types
+
+import torch
+import torchaudio
from funasr.fileio.read_text import read_2column_text
@@ -32,6 +36,7 @@
always_2d: bool = False,
normalize: bool = False,
dest_sample_rate: int = 16000,
+ speed_perturb: Union[list, tuple] = None,
):
assert check_argument_types()
self.fname = fname
@@ -40,19 +45,31 @@
self.normalize = normalize
self.data = read_2column_text(fname)
self.dest_sample_rate = dest_sample_rate
+ self.speed_perturb = speed_perturb
def __getitem__(self, key):
wav = self.data[key]
if self.normalize:
# soundfile.read normalizes data to [-1,1] if dtype is not given
array, rate = librosa.load(
- wav, sr=self.dest_sample_rate, mono=not self.always_2d
+ wav, sr=self.dest_sample_rate, mono=self.always_2d
)
else:
array, rate = librosa.load(
- wav, sr=self.dest_sample_rate, mono=not self.always_2d, dtype=self.dtype
+ wav, sr=self.dest_sample_rate, mono=self.always_2d, dtype=self.dtype
)
+ if self.speed_perturb is not None:
+ speed = random.choice(self.speed_perturb)
+ if speed != 1.0:
+ array, _ = torchaudio.sox_effects.apply_effects_tensor(
+ torch.tensor(array).view(1, -1), rate,
+ [['speed', str(speed)], ['rate', str(rate)]])
+ array = array.view(-1).numpy()
+
+ if array.ndim==2:
+ array=array.transpose((1, 0))
+
return rate, array
def get_path(self, key):
--
Gitblit v1.9.1