Ma/auto-caption
1
0
Fork 0
mirror of https://github.com/HiMeditator/auto-caption.git synced 2026-02-13 19:23:26 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat(engine): 重构字幕引擎，新增 Sherpa-ONNX SenseVoice 语音识别模型

Browse Source 
- 重构字幕引擎，将音频采集改为在新线程上进行
- 重构 audio2text 中的类，调整运行逻辑
- 更新 main 函数，添加对 Sosv 模型的支持
- 修改 AudioStream 类，默认使用 16000Hz 采样率
This commit is contained in:
himeditator
2025-09-06 20:49:46 +08:00
parent 2b7ce06f04
commit eba2c5ca45
14 changed files with 377 additions and 112 deletions
Download Patch File Download Diff File Expand all files Collapse all files

40
engine/sysaudio/darwin.py
View File

@@ -37,14 +37,13 @@ class AudioStream:
self.FORMAT = pyaudio.paInt16
self.SAMP_WIDTH = pyaudio.get_sample_size(self.FORMAT)
self.CHANNELS = int(self.device["maxInputChannels"])
self.RATE = int(self.device["defaultSampleRate"])
self.CHUNK = self.RATE // chunk_rate
self.DEFAULT_RATE = int(self.device["defaultSampleRate"])
self.CHUNK_RATE = chunk_rate
def reset_chunk_size(self, chunk_size: int):
"""
重新设置音频块大小
"""
self.CHUNK = chunk_size
self.RATE = 16000
self.CHUNK = self.RATE // self.CHUNK_RATE
self.open_stream()
self.close_stream()
def get_info(self):
dev_info = f"""
@@ -72,16 +71,27 @@ class AudioStream:
打开并返回系统音频输出流
"""
if self.stream: return self.stream
self.stream = self.mic.open(
format = self.FORMAT,
channels = int(self.CHANNELS),
rate = self.RATE,
input = True,
input_device_index = int(self.INDEX)
)
try:
self.stream = self.mic.open(
format = self.FORMAT,
channels = int(self.CHANNELS),
rate = self.RATE,
input = True,
input_device_index = int(self.INDEX)
)
except OSError:
self.RATE = self.DEFAULT_RATE
self.CHUNK = self.RATE // self.CHUNK_RATE
self.stream = self.mic.open(
format = self.FORMAT,
channels = int(self.CHANNELS),
rate = self.RATE,
input = True,
input_device_index = int(self.INDEX)
)
return self.stream
def read_chunk(self):
def read_chunk(self) -> bytes | None:
"""
读取音频数据
"""

11
engine/sysaudio/linux.py
View File

@@ -55,15 +55,10 @@ class AudioStream:
self.FORMAT = 16
self.SAMP_WIDTH = 2
self.CHANNELS = 2
self.RATE = 48000
self.RATE = 16000
self.CHUNK_RATE = chunk_rate
self.CHUNK = self.RATE // chunk_rate
def reset_chunk_size(self, chunk_size: int):
"""
重新设置音频块大小
"""
self.CHUNK = chunk_size
def get_info(self):
dev_info = f"""
音频捕获进程：
@@ -84,7 +79,7 @@ class AudioStream:
启动音频捕获进程
"""
self.process = subprocess.Popen(
["parec", "-d", self.source, "--format=s16le", "--rate=48000", "--channels=2"],
["parec", "-d", self.source, "--format=s16le", "--rate=16000", "--channels=2"],
stdout=subprocess.PIPE
)

38
engine/sysaudio/win.py
View File

@@ -61,14 +61,13 @@ class AudioStream:
self.FORMAT = pyaudio.paInt16
self.SAMP_WIDTH = pyaudio.get_sample_size(self.FORMAT)
self.CHANNELS = int(self.device["maxInputChannels"])
self.RATE = int(self.device["defaultSampleRate"])
self.CHUNK = self.RATE // chunk_rate
self.DEFAULT_RATE = int(self.device["defaultSampleRate"])
self.CHUNK_RATE = chunk_rate
def reset_chunk_size(self, chunk_size: int):
"""
重新设置音频块大小
"""
self.CHUNK = chunk_size
self.RATE = 16000
self.CHUNK = self.RATE // self.CHUNK_RATE
self.open_stream()
self.close_stream()
def get_info(self):
dev_info = f"""
@@ -96,13 +95,24 @@ class AudioStream:
打开并返回系统音频输出流
"""
if self.stream: return self.stream
self.stream = self.mic.open(
format = self.FORMAT,
channels = self.CHANNELS,
rate = self.RATE,
input = True,
input_device_index = self.INDEX
)
try:
self.stream = self.mic.open(
format = self.FORMAT,
channels = self.CHANNELS,
rate = self.RATE,
input = True,
input_device_index = self.INDEX
)
except OSError:
self.RATE = self.DEFAULT_RATE
self.CHUNK = self.RATE // self.CHUNK_RATE
self.stream = self.mic.open(
format = self.FORMAT,
channels = self.CHANNELS,
rate = self.RATE,
input = True,
input_device_index = self.INDEX
)
return self.stream
def read_chunk(self) -> bytes | None: