Repository navigation
Expand file tree
/
Copy pathvoice.py
More file actions
108 lines (79 loc) · 2.85 KB
/
Copy pathvoice.py
File metadata and controls
108 lines (79 loc) · 2.85 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
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
import math
import os
import queue
import tempfile
import time
from aider.llm import litellm
try:
import soundfile as sf
except (OSError, ModuleNotFoundError):
sf = None
from prompt_toolkit.shortcuts import prompt
from .dump import dump # noqa: F401
class SoundDeviceError(Exception):
pass
class Voice:
max_rms = 0
min_rms = 1e5
pct = 0
threshold = 0.15
def __init__(self):
if sf is None:
raise SoundDeviceError
try:
print("Initializing sound device...")
import sounddevice as sd
self.sd = sd
except (OSError, ModuleNotFoundError):
raise SoundDeviceError
def callback(self, indata, frames, time, status):
"""This is called (from a separate thread) for each audio block."""
import numpy as np
rms = np.sqrt(np.mean(indata**2))
self.max_rms = max(self.max_rms, rms)
self.min_rms = min(self.min_rms, rms)
rng = self.max_rms - self.min_rms
if rng > 0.001:
self.pct = (rms - self.min_rms) / rng
else:
self.pct = 0.5
self.q.put(indata.copy())
def get_prompt(self):
num = 10
if math.isnan(self.pct) or self.pct < self.threshold:
cnt = 0
else:
cnt = int(self.pct * 10)
bar = "░" * cnt + "█" * (num - cnt)
bar = bar[:num]
dur = time.time() - self.start_time
return f"Recording, press ENTER when done... {dur:.1f}sec {bar}"
def record_and_transcribe(self, history=None, language=None):
try:
return self.raw_record_and_transcribe(history, language)
except KeyboardInterrupt:
return
def raw_record_and_transcribe(self, history, language):
self.q = queue.Queue()
filename = tempfile.mktemp(suffix=".wav")
try:
sample_rate = int(self.sd.query_devices(None, "input")["default_samplerate"])
except (TypeError, ValueError):
sample_rate = 16000 # fallback to 16kHz if unable to query device
self.start_time = time.time()
with self.sd.InputStream(samplerate=sample_rate, channels=1, callback=self.callback):
prompt(self.get_prompt, refresh_interval=0.1)
with sf.SoundFile(filename, mode="x", samplerate=sample_rate, channels=1) as file:
while not self.q.empty():
file.write(self.q.get())
with open(filename, "rb") as fh:
transcript = litellm.transcription(
model="whisper-1", file=fh, prompt=history, language=language
)
text = transcript.text
return 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(Voice().record_and_transcribe())