museasr.py
2.61 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
###############################################################################
# Copyright (C) 2024 LiveTalking@lipku https://github.com/lipku/LiveTalking
# email: lipku@foxmail.com
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
###############################################################################
import time
import numpy as np
import queue
from queue import Queue
#import multiprocessing as mp
from baseasr import BaseASR
from musetalk.whisper.audio2feature import Audio2Feature
class MuseASR(BaseASR):
def __init__(self, opt, parent,audio_processor:Audio2Feature):
super().__init__(opt,parent)
self.audio_processor = audio_processor
def run_step(self):
############################################## extract audio feature ##############################################
start_time = time.time()
for _ in range(self.batch_size*2):
audio_frame,type,eventpoint = self.get_audio_frame()
self.frames.append(audio_frame)
self.output_queue.put((audio_frame,type,eventpoint))
if len(self.frames) <= self.stride_left_size + self.stride_right_size:
return
inputs = np.concatenate(self.frames) # [N * chunk]
whisper_feature = self.audio_processor.audio2feat(inputs)
# for feature in whisper_feature:
# self.audio_feats.append(feature)
#print(f"processing audio costs {(time.time() - start_time) * 1000}ms, inputs shape:{inputs.shape} whisper_feature len:{len(whisper_feature)}")
whisper_chunks = self.audio_processor.feature2chunks(feature_array=whisper_feature,fps=self.fps/2,batch_size=self.batch_size,start=self.stride_left_size/2 )
#print(f"whisper_chunks len:{len(whisper_chunks)},self.audio_feats len:{len(self.audio_feats)},self.output_queue len:{self.output_queue.qsize()}")
#self.audio_feats = self.audio_feats[-(self.stride_left_size + self.stride_right_size):]
self.feat_queue.put(whisper_chunks)
# discard the old part to save memory
self.frames = self.frames[-(self.stride_left_size + self.stride_right_size):]