RealTimeSTT 0.2.2__tar.gz → 0.2.3__tar.gz

{RealtimeSTT-0.2.2 → RealtimeSTT-0.2.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: RealtimeSTT
-Version: 0.2.2
+Version: 0.2.3
 Summary: A fast Voice Activity Detection and Transcription System
 Home-page: https://github.com/KoljaB/RealTimeSTT
 Author: Kolja Beigel
@@ -12,6 +12,16 @@ Classifier: Operating System :: OS Independent
 Requires-Python: >=3.6
 Description-Content-Type: text/markdown
 License-File: LICENSE
+Requires-Dist: PyAudio==0.2.14
+Requires-Dist: faster-whisper==1.0.3
+Requires-Dist: pvporcupine==1.9.5
+Requires-Dist: webrtcvad==2.0.10
+Requires-Dist: halo==0.0.31
+Requires-Dist: torch==2.3.1
+Requires-Dist: torchaudio==2.3.1
+Requires-Dist: scipy==1.12.0
+Requires-Dist: websockets==v12.0
+Requires-Dist: openwakeword==0.6.0
 
 
 # RealtimeSTT

{RealtimeSTT-0.2.2 → RealtimeSTT-0.2.3}/RealtimeSTT/audio_recorder.py

@@ -229,7 +229,7 @@ class AudioToTextRecorder:
             pre-trained model from Silero in the ONNX (Open Neural Network
             Exchange) format instead of the PyTorch format. This is
             recommended for faster performance.
-		- silero_deactivity_detection (bool, default=False): Enables the Silero
+        - silero_deactivity_detection (bool, default=False): Enables the Silero
             model for end-of-speech detection. More robust against background
             noise. Utilizes additional GPU resources but improves accuracy in
             noisy environments. When False, uses the default WebRTC VAD,
@@ -410,6 +410,10 @@ class AudioToTextRecorder:
         self.initial_prompt = initial_prompt
         self.suppress_tokens = suppress_tokens
         self.use_wake_words = wake_words or wakeword_backend in {'oww', 'openwakeword', 'openwakewords'}
+        self.detected_language = None
+        self.detected_language_probability = 0
+        self.detected_realtime_language = None
+        self.detected_realtime_language_probability = 0
 
         # Initialize the logging configuration with the specified level
         log_format = 'RealTimeSTT: %(name)s - %(levelname)s - %(message)s'
@@ -758,17 +762,16 @@ class AudioToTextRecorder:
                 if conn.poll(0.5):
                     audio, language = conn.recv()
                     try:
-                        segments = model.transcribe(
+                        segments, info = model.transcribe(
                             audio,
                             language=language if language else None,
                             beam_size=beam_size,
                             initial_prompt=initial_prompt,
                             suppress_tokens=suppress_tokens
                         )
-                        segments = segments[0]
                         transcription = " ".join(seg.text for seg in segments)
                         transcription = transcription.strip()
-                        conn.send(('success', transcription))
+                        conn.send(('success', (transcription, info)))
                     except Exception as e:
                         logging.error(f"General transcription error: {e}")
                         conn.send(('error', str(e)))
@@ -969,8 +972,11 @@ class AudioToTextRecorder:
 
         self._set_state("inactive")
         if status == 'success':
+            segments, info = result
+            self.detected_language = info.language if info.language_probability > 0 else None
+            self.detected_language_probability = info.language_probability
             self.last_transcription_bytes = audio_copy
-            return self._preprocess_output(result)
+            return self._preprocess_output(segments)
         else:
             logging.error(result)
             raise Exception(result)
@@ -1447,7 +1453,7 @@ class AudioToTextRecorder:
                         INT16_MAX_ABS_VALUE
 
                     # Perform transcription and assemble the text
-                    segments = self.realtime_model_type.transcribe(
+                    segments, info = self.realtime_model_type.transcribe(
                         audio_array,
                         language=self.language if self.language else None,
                         beam_size=self.beam_size_realtime,
@@ -1455,6 +1461,9 @@ class AudioToTextRecorder:
                         suppress_tokens=self.suppress_tokens,
                     )
 
+                    self.detected_realtime_language = info.language if info.language_probability > 0 else None
+                    self.detected_realtime_language_probability = info.language_probability
+
                     # double check recording state
                     # because it could have changed mid-transcription
                     if self.is_recording and time.time() - \
@@ -1462,7 +1471,7 @@ class AudioToTextRecorder:
 
                         logging.debug('Starting realtime transcription')
                         self.realtime_transcription_text = " ".join(
-                            seg.text for seg in segments[0]
+                            seg.text for seg in segments
                         )
                         self.realtime_transcription_text = \
                             self.realtime_transcription_text.strip()

{RealtimeSTT-0.2.2 → RealtimeSTT-0.2.3}/RealtimeSTT.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: RealtimeSTT
-Version: 0.2.2
+Version: 0.2.3
 Summary: A fast Voice Activity Detection and Transcription System
 Home-page: https://github.com/KoljaB/RealTimeSTT
 Author: Kolja Beigel
@@ -12,6 +12,16 @@ Classifier: Operating System :: OS Independent
 Requires-Python: >=3.6
 Description-Content-Type: text/markdown
 License-File: LICENSE
+Requires-Dist: PyAudio==0.2.14
+Requires-Dist: faster-whisper==1.0.3
+Requires-Dist: pvporcupine==1.9.5
+Requires-Dist: webrtcvad==2.0.10
+Requires-Dist: halo==0.0.31
+Requires-Dist: torch==2.3.1
+Requires-Dist: torchaudio==2.3.1
+Requires-Dist: scipy==1.12.0
+Requires-Dist: websockets==v12.0
+Requires-Dist: openwakeword==0.6.0
 
 
 # RealtimeSTT

{RealtimeSTT-0.2.2 → RealtimeSTT-0.2.3}/setup.py

@@ -9,7 +9,7 @@ with open('requirements.txt') as f:
 
 setuptools.setup(
     name="RealtimeSTT",
-    version="0.2.2",
+    version="0.2.3",
     author="Kolja Beigel",
     author_email="kolja.beigel@web.de",
     description="A fast Voice Activity Detection and Transcription System",