You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
86 lines
2.8 KiB
Python
86 lines
2.8 KiB
Python
###############################################################################
|
|
# 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
|
|
|
|
|
|
class BaseASR:
|
|
def __init__(self, opt, parent=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): #16khz 20ms pcm
|
|
self.queue.put(audio_chunk)
|
|
|
|
def get_audio_frame(self):
|
|
try:
|
|
frame = 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
|
|
|
|
return frame,type
|
|
|
|
def is_audio_frame_empty(self)->bool:
|
|
return self.queue.empty()
|
|
|
|
def get_audio_out(self): #get origin audio pcm to nerf
|
|
return self.output_queue.get()
|
|
|
|
def warm_up(self):
|
|
for _ in range(self.stride_left_size + self.stride_right_size):
|
|
audio_frame,type=self.get_audio_frame()
|
|
self.frames.append(audio_frame)
|
|
self.output_queue.put((audio_frame,type))
|
|
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) |