baseasr.py
3.05 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
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
###############################################################################
# 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 torch.multiprocessing as mp
from basereal import BaseReal
class BaseASR:
def __init__(self, opt, parent:BaseReal = None):
self.opt = opt
self.parent = parent
self.fps = opt.fps # 20 ms per frame
self.sample_rate = 16000
self.chunk = self.sample_rate // self.fps # 320 samples per chunk (20ms * 16000 / 1000)
self.queue = Queue()
self.output_queue = mp.Queue()
self.batch_size = opt.batch_size
self.frames = []
self.stride_left_size = opt.l
self.stride_right_size = opt.r
#self.context_size = 10
self.feat_queue = mp.Queue(2)
#self.warm_up()
def flush_talk(self):
self.queue.queue.clear()
def put_audio_frame(self,audio_chunk,eventpoint=None): #16khz 20ms pcm
self.queue.put((audio_chunk,eventpoint))
#return frame:audio pcm; type: 0-normal speak, 1-silence; eventpoint:custom event sync with audio
def get_audio_frame(self):
try:
frame,eventpoint = self.queue.get(block=True,timeout=0.01)
type = 0
#print(f'[INFO] get frame {frame.shape}')
except queue.Empty:
if self.parent and self.parent.curr_state>1: #播放自定义音频
frame = self.parent.get_audio_stream(self.parent.curr_state)
type = self.parent.curr_state
else:
frame = np.zeros(self.chunk, dtype=np.float32)
type = 1
eventpoint = None
return frame,type,eventpoint
#return frame:audio pcm; type: 0-normal speak, 1-silence; eventpoint:custom event sync with audio
def get_audio_out(self):
return self.output_queue.get()
def warm_up(self):
for _ in range(self.stride_left_size + self.stride_right_size):
audio_frame,type,eventpoint=self.get_audio_frame()
self.frames.append(audio_frame)
self.output_queue.put((audio_frame,type,eventpoint))
for _ in range(self.stride_left_size):
self.output_queue.get()
def run_step(self):
pass
def get_next_feat(self,block,timeout):
return self.feat_queue.get(block,timeout)