ExternalVendorCode/lollms
1
0
Fork 0
mirror of https://github.com/ParisNeo/lollms.git synced 2024-12-19 20:57:58 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

fixed voice recording

Browse Source
This commit is contained in:
Saifeddine ALOUI 2024-09-12 22:23:35 +02:00
parent a1c63689f7
commit ffcd2df36c
1 changed files with 18 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
lollms/media.py
View File

@ -473,6 +473,7 @@ import sounddevice as sd
import threading import threading
import datetime import datetime
import wave import wave
import numpy as np
class AudioNinja: class AudioNinja:
def __init__(self, lc, logs_folder='logs', device=None): def __init__(self, lc, logs_folder='logs', device=None):
@ -503,12 +504,14 @@ class AudioNinja:
Internal method to handle audio recording callback. Internal method to handle audio recording callback.
""" """
def callback(indata, frames, time, status): def callback(indata, frames, time, status):
if status:
self.lc.warning(f"Status: {status}")
if self.is_recording: if self.is_recording:
self.frames.append(indata.copy()) self.frames.append(indata.copy())
with sd.InputStream(callback=callback, device=self.device, channels=self.channels, samplerate=self.sample_rate): with sd.InputStream(callback=callback, device=self.device, channels=self.channels, samplerate=self.sample_rate):
while self.is_recording: while self.is_recording:
sd.sleep(1000) sd.sleep(100)
def start_recording(self): def start_recording(self):
""" """
@ -538,15 +541,26 @@ class AudioNinja:
""" """
timestamp = datetime.datetime.now().strftime("%Y%m%d_%H%M%S") timestamp = datetime.datetime.now().strftime("%Y%m%d_%H%M%S")
filename = self.logs_folder / f"recording_{timestamp}.wav" filename = self.logs_folder / f"recording_{timestamp}.wav"
with wave.open(filename, 'wb') as wf:
audio_data = np.concatenate(self.frames, axis=0)
# Normalize float32 data to the range [-1, 1]
audio_data = np.clip(audio_data, -1, 1)
# Convert to int16
audio_data = (audio_data * 32767).astype(np.int16)
with wave.open(str(filename), 'wb') as wf:
wf.setnchannels(self.channels) wf.setnchannels(self.channels)
wf.setsampwidth(sd.default.dtype[0].itemsize) wf.setsampwidth(2) # 2 bytes for int16
wf.setframerate(self.sample_rate) wf.setframerate(self.sample_rate)
wf.writeframes(b''.join(self.frames)) wf.writeframes(audio_data.tobytes())
self.lc.info(f"Ninja stored the audio file at '{filename}'! 🥷📂") self.lc.info(f"Ninja stored the audio file at '{filename}'! 🥷📂")
return filename return filename
class WebcamImageSender: class WebcamImageSender:
""" """
Class for capturing images from the webcam and sending them to a SocketIO client. Class for capturing images from the webcam and sending them to a SocketIO client.