gitea/conjurer
1
0
Fork 0
mirror of https://github.com/migatu/conjurer.git synced 2026-07-14 21:38:38 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fx test

Browse Source
This commit is contained in:
mtuszowski
2024-09-20 16:06:05 +02:00
parent 4184cbb687
commit 0278dc3a49
1 changed files with 24 additions and 23 deletions
Download Patch File Download Diff File Expand all files Collapse all files
voice_recognition.py
+24 -23
View File
@@ -21,6 +21,11 @@ SAMPLING_RATE = OpusDecoder.SAMPLING_RATE
logger = logging.getLogger("discord")
location = "/home/pi/Conjurer/transcripts/"
class CommunicationObject:
def __init__(self, msg_type, user, data):
self.type = msg_type
self.user = user
self.data = data
class WaveWriter:
def __init__(self, user_id, queue):
@@ -67,11 +72,7 @@ class WaveWriter:
self.transcript_file_future.setnchannels(CHANNELS)
self.transcript_file_future.setsampwidth(SAMPLE_WIDTH)
self.transcript_file_future.setframerate(SAMPLING_RATE)
operation = {
"type": "user_cleanup",
"user" : self.user,
"filename": self.file_name_present
}
operation = CommunicationObject(msg_type="send_file",user=self.user,data=[self.file_name_present])
logger.info("After rotation")
logger.info(self.file_name_present)
logger.info(self.file_name_past)
@@ -131,13 +132,6 @@ class Transcriber(commands.Cog):
self.comm_queue = queue
self.worker = worker
self.wsink = SRBuffer(self.comm_queue)
async def transcribe(self,file_url):
config = aai.TranscriptionConfig(speaker_labels=True, language_code="pl")
transcriber = aai.Transcriber()
transcript = transcriber.transcribe(file_url, config=config)
for utterance in transcript.utterances:
logger.info("Speaker %s : %s", utterance.speaker, utterance.text)
@commands.hybrid_command(name="transcribe")
async def test(self, ctx):
@@ -171,7 +165,6 @@ class Transcriber(commands.Cog):
item[2] = time.time_ns()
item[4] = False
item[0].rotate()
await self.transcribe(item[0].file_name_past)
item[3] = False
@commands.Cog.listener()
@@ -185,11 +178,7 @@ class Transcriber(commands.Cog):
self.wsink.on_user_connect(user)
elif after.channel is None:
logger.info("User %s disconnected from channel %s", user, before.channel.name)
operation = {
"type": "user_cleanup",
"user" : user,
"filename": None
}
operation = CommunicationObject(msg_type="user_cleanup", user=user, data=None)
self.comm_queue.put(operation)
else:
logger.info("User VC status changed %s", user.id)
@@ -200,22 +189,34 @@ class Transcriber(commands.Cog):
@commands.command(name="stop_transcribe")
async def stop(self, ctx):
self.check_data.stop()
self.comm_queue.put("STOP")
stop_token = CommunicationObject("STOP",None,None)
self.comm_queue.put(stop_token)
await ctx.voice_client.disconnect()
def transcribe_output_queue(queue):
logger.info("Worker start")
logger.info("Transcript worker start")
config = aai.TranscriptionConfig(speaker_labels=True, language_code="pl")
transcriber = aai.Transcriber()
while True:
item = queue.get()
if item == "STOP":
if item.type == "STOP":
logger.info("Queue ended")
break
logger.info("PING")
elif item.type == "send_file":
transcript = ""
for iter in item.data:
transcript = transcriber.transcribe(iter, config=config)
for utterance in transcript.utterances:
logger.info("%s : %s", item.user, utterance.text)
elif item.type == "user_cleanup":
logger.info("User %s disconnected - cleanup action")
logger.info("End transcript worker")
async def setup(bot):
logger = logging.getLogger("discord")
logger.info("Loading voice transcribed module phase one")
worker = threading.Thread(target=transcribe_output_queue)
logger.info("Loading voice transcribed phase two")
logger.info("Loading voice transcribed phasetwo")
queue = Queue()
logger.info("Loading voice transcribed module phase three")
await bot.add_cog(Transcriber(bot, worker, queue))