Spaces:
Configuration error
Configuration error
File size: 3,037 Bytes
313814b |
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 |
# TODO: move out of `speaches` package
import asyncio
import signal
import httpx
from httpx_ws import AsyncWebSocketSession, WebSocketDisconnect, aconnect_ws
from wsproto.connection import ConnectionState
CHUNK = 1024 * 4
AUDIO_RECORD_CMD = "arecord -D default -f S16_LE -r 16000 -c 1 -t raw"
COPY_TO_CLIPBOARD_CMD = "wl-copy"
NOTIFY_CMD = "notify-desktop"
client = httpx.AsyncClient(base_url="ws://localhost:8000")
async def audio_sender(ws: AsyncWebSocketSession) -> None:
process = await asyncio.create_subprocess_shell(
AUDIO_RECORD_CMD,
stdout=asyncio.subprocess.PIPE,
stderr=asyncio.subprocess.DEVNULL,
)
assert process.stdout is not None
try:
while not process.stdout.at_eof():
data = await process.stdout.read(CHUNK)
if ws.connection.state != ConnectionState.OPEN:
break
await ws.send_bytes(data)
except Exception as e:
print(e)
finally:
process.kill()
async def transcription_receiver(ws: AsyncWebSocketSession) -> None:
transcription = ""
notification_id: int | None = None
try:
while True:
data = await ws.receive_text()
if not data:
break
transcription += data
await copy_to_clipboard(transcription)
notification_id = await notify(transcription, replaces_id=notification_id)
except WebSocketDisconnect:
pass
print(transcription)
async def copy_to_clipboard(text: str) -> None:
process = await asyncio.create_subprocess_shell(
COPY_TO_CLIPBOARD_CMD, stdin=asyncio.subprocess.PIPE
)
await process.communicate(input=text.encode("utf-8"))
await process.wait()
async def notify(text: str, replaces_id: int | None = None) -> int:
cmd = ["notify-desktop", "--app-name", "Speaches"]
if replaces_id is not None:
cmd.extend(["--replaces-id", str(replaces_id)])
cmd.append("'Speaches'")
cmd.append(f"'{text}'")
process = await asyncio.create_subprocess_shell(
" ".join(cmd),
stdout=asyncio.subprocess.PIPE,
)
await process.wait()
assert process.stdout is not None
notification_id = (await process.stdout.read()).decode("utf-8")
return int(notification_id)
async def main() -> None:
async with aconnect_ws("/v1/audio/transcriptions", client) as ws:
async with asyncio.TaskGroup() as tg:
sender_task = tg.create_task(audio_sender(ws))
receiver_task = tg.create_task(transcription_receiver(ws))
async def on_interrupt():
sender_task.cancel()
receiver_task.cancel()
await asyncio.gather(sender_task, receiver_task)
asyncio.get_running_loop().add_signal_handler(
signal.SIGINT,
lambda: asyncio.create_task(on_interrupt()),
)
asyncio.run(main())
# poetry --directory /home/nixos/code/speaches run python /home/nixos/code/speaches/speaches/client.py
|