Test

sr_example.py

@@ -78,7 +78,7 @@ else:
             *,
             process_cb: Optional[SRProcessDataCB] = None,
             text_cb: Optional[SRTextCB] = None,
-            default_recognizer: SRRecognizerMethod = 'google',
+            default_recognizer: SRRecognizerMethod = 'assemblyai',
             phrase_time_limit: int = 10,
             ignore_silence_packets: bool = True,
         ):

voice_example.py

@@ -0,0 +1,47 @@
+# -*- coding: utf-8 -*-
+
+import discord
+from discord.ext import commands, voice_recv
+
+discord.opus._load_default()
+
+bot = commands.Bot(command_prefix=commands.when_mentioned, intents=discord.Intents.all())
+
+class Testing(commands.Cog):
+    def __init__(self, bot):
+        self.bot = bot
+
+    @commands.command()
+    async def test(self, ctx):
+        def callback(user, data: voice_recv.VoiceData):
+            print(f"Got packet from {user}")
+
+            ## voice power level, how loud the user is speaking
+            # ext_data = packet.extension_data.get(voice_recv.ExtensionID.audio_power)
+            # value = int.from_bytes(ext_data, 'big')
+            # power = 127-(value & 127)
+            # print('#' * int(power * (79/128)))
+            ## instead of 79 you can use shutil.get_terminal_size().columns-1
+
+        vc = await ctx.author.voice.channel.connect(cls=voice_recv.VoiceRecvClient)
+        vc.listen(voice_recv.BasicSink(callback))
+
+    @commands.command()
+    async def stop(self, ctx):
+        await ctx.voice_client.disconnect()
+
+    @commands.command()
+    async def die(self, ctx):
+        ctx.voice_client.stop()
+        await ctx.bot.close()
+
+@bot.event
+async def on_ready():
+    print('Logged in as {0.id}/{0}'.format(bot.user))
+    print('------')
+    await bot.add_cog(Testing(bot))
+
+REMOTE_HOST_NAME = "discord"
+
+
+bot.run("NzUxNDQxODgzNDA2MDA4NDEw.Go--wb.Nr28Oo4eYAP1p2XFVHF5uIQfcPD7s_jO2NfMCQ")

voice_recognition.py

@@ -20,27 +20,35 @@ FILE_URL = "https://github.com/AssemblyAI-Community/audio-examples/raw/main/2023
 
 logger = logging.getLogger("discord")
 
+
+class SRAudioSinkHammerVersion(AudioSink):
+    def __init__(
+    self,
+    *,
+    process_cb: Optional[SRProcessDataCB] = None,
+    text_cb: Optional[SRTextCB] = None,
+    default_recognizer: SRRecognizerMethod = 'google',
+    phrase_time_limit: int = 10,
+    ignore_silence_packets: bool = True,
+):
+    super().__init__(None)
+    self.process_cb: Optional[SRProcessDataCB] = process_cb
+    self.text_cb: Optional[SRTextCB] = text_cb
+    self.phrase_time_limmit: int = phrase_time_limit
+    self.ignore_silence_packets: bool = ignore_silence_packets
+
+    self.default_recognizer: SRRecognizerMethod = default_recognizer
+    self._stream_data: defaultdict[int, _StreamData] = defaultdict(
+        lambda: _StreamData(stopper=None, recognizer=sr.Recognizer(), buffer=array.array('B'))
+    )
+
+
+
 class Transcriber(commands.Cog):
     def __init__(self, bot):
         self.bot = bot
         self._last_member = None
 
-    
-    @commands.Cog.listener()
-    async def on_member_join(self, member):
-        channel = member.guild.system_channel
-        if channel is not None:
-            await channel.send(f'Witaj u Nas {member.mention}.')
-
-    @commands.hybrid_command(name="witaj")
-    async def witaj(self, ctx, *, member: discord.Member = None):
-        """Says hello"""
-        member = member or ctx.author
-        if self._last_member is None or self._last_member.id != member.id:
-            await ctx.send(f'Mhm {member.name}~')
-        else:
-            await ctx.send(f'Powtarzas sie {member.name}')
-        self._last_member = member
     async def transcribe():
         config = aai.TranscriptionConfig(speaker_labels=True)
 
@@ -51,7 +59,7 @@ class Transcriber(commands.Cog):
         )
         for utterance in transcript.utterances:
           print(f"Speaker {utterance.speaker}: {utterance.text}")
-    @commands.hybrid_command(name="connect_for_transcribe")
+    @commands.hybrid_command(name="transcribe")
     async def test(self, ctx):
         def callback(user, data: voice_recv.VoiceData):
             print(f"Got packet from {user}")
@@ -71,10 +79,5 @@ class Transcriber(commands.Cog):
     async def stop(self, ctx):
         await ctx.voice_client.disconnect()
 
-    @commands.command(name="kill_transcribe_client")
-    async def die(self, ctx):
-        ctx.voice_client.stop()
-        await ctx.bot.close()
-
 async def setup(bot):
     await bot.add_cog(Transcriber(bot))