mirror of
https://github.com/Aider-AI/aider.git
synced 2025-05-31 01:35:00 +00:00
1f42b0839f
# Aider chat conversation:
USER: I ran this command:
python -m aider.voice
And got this output:
Traceback (most recent call last):
File "<frozen runpy>", line 198, in _run_module_as_main
File "<frozen runpy>", line 88, in _run_code
File "/Users/gauthier/Projects/aider/aider/voice.py", line 42, in <module>
print(record_and_transcribe(api_key))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/gauthier/Projects/aider/aider/voice.py", line 22, in record_and_transcribe
recording = sd.rec(int(sample_rate * duration), samplerate=sample_rate, channels=1, callback=on_key_press)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/gauthier/Projects/aider/.venv/lib/python3.11/site-packages/sounddevice.py", line 276, in rec
ctx.start_stream(InputStream, samplerate, ctx.input_channels,
TypeError: _CallbackContext.start_stream() got multiple values for argument 'callback'
Recording started, press any key to stop...
ASSISTANT: It seems like there's an issue with the way the `callback` argument is being passed to the `sd.rec` function in the `record_and_transcribe` function in the `aider/voice.py` file.
The `sd.rec` function is a convenience function that internally creates an instance of `sd.InputStream` and starts recording. The `callback` argument should be passed to the `sd.InputStream` constructor, not the `sd.rec` function.
Here's how we can fix this:
1. Modify the `aider/voice.py` file.
```python
aider/voice.py
<<<<<<< HEAD
recording = sd.rec(int(sample_rate * duration), samplerate=sample_rate, channels=1, callback=on_key_press)
=======
# Create an instance of InputStream with the callback
stream = sd.InputStream(samplerate=sample_rate, channels=1, callback=on_key_press)
stream.start()
recording = sd.rec(int(sample_rate * duration), samplerate=sample_rate, channels=1)
>>>>>>> updated
```
This change creates an instance of `sd.InputStream` with the `on_key_press` callback and starts the stream before calling `sd.rec`. This should ensure that the callback is correctly passed to the `InputStream` and not the `rec` function.
45 lines
1.4 KiB
Python
45 lines
1.4 KiB
Python
import sounddevice as sd
|
|
import numpy as np
|
|
import keyboard
|
|
import openai
|
|
import io
|
|
|
|
import os
|
|
|
|
def record_and_transcribe(api_key):
|
|
|
|
# Set the sample rate and duration for the recording
|
|
sample_rate = 16000 # 16kHz
|
|
duration = 10 # in seconds
|
|
|
|
# Create a callback function to stop recording when a key is pressed
|
|
def on_key_press(e):
|
|
print("Key pressed, stopping recording...")
|
|
sd.stop()
|
|
|
|
# Start the recording
|
|
print("Recording started, press any key to stop...")
|
|
# Create an instance of InputStream with the callback
|
|
stream = sd.InputStream(samplerate=sample_rate, channels=1, callback=on_key_press)
|
|
stream.start()
|
|
recording = sd.rec(int(sample_rate * duration), samplerate=sample_rate, channels=1)
|
|
|
|
# Wait for a key press
|
|
keyboard.wait()
|
|
|
|
# Convert the recording to bytes
|
|
recording_bytes = io.BytesIO()
|
|
np.save(recording_bytes, recording, allow_pickle=False)
|
|
recording_bytes = recording_bytes.getvalue()
|
|
|
|
# Transcribe the audio using the Whisper API
|
|
response = openai.Whisper.asr.create(audio_data=recording_bytes)
|
|
|
|
# Return the transcription
|
|
return response['choices'][0]['text']
|
|
|
|
if __name__ == "__main__":
|
|
api_key = os.getenv('OPENAI_API_KEY')
|
|
if not api_key:
|
|
raise ValueError("Please set the OPENAI_API_KEY environment variable.")
|
|
print(record_and_transcribe(api_key))
|