RealTimeSTT 0.1.7__tar.gz → 0.1.9__tar.gz

RealTimeSTT-0.1.9/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2023 Kolja Beigel
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

{RealTimeSTT-0.1.7/RealTimeSTT.egg-info → RealTimeSTT-0.1.9}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: RealTimeSTT
-Version: 0.1.7
+Version: 0.1.9
 Summary: A fast Voice Activity Detection and Transcription System
 Home-page: https://github.com/KoljaB/RealTimeSTT
 Author: Kolja Beigel
@@ -11,13 +11,14 @@ Classifier: License :: OSI Approved :: MIT License
 Classifier: Operating System :: OS Independent
 Requires-Python: >=3.6
 Description-Content-Type: text/markdown
-Requires-Dist: PyAudio>=0.2.13
-Requires-Dist: faster-whisper>=0.7.1
+License-File: LICENSE
+Requires-Dist: PyAudio==0.2.14
+Requires-Dist: faster-whisper==0.10.0
 Requires-Dist: pvporcupine==1.9.5
-Requires-Dist: webrtcvad>=2.0.10
-Requires-Dist: halo>=0.0.31
-Requires-Dist: torch>=2.0.1
-Requires-Dist: torchaudio>=2.0.2
+Requires-Dist: webrtcvad==2.0.10
+Requires-Dist: halo==0.0.31
+Requires-Dist: torch==2.1.2
+Requires-Dist: torchaudio==2.1.2
 
 
 # RealtimeSTT
@@ -37,6 +38,17 @@ https://github.com/KoljaB/RealtimeSTT/assets/7604638/207cb9a2-4482-48e7-9d2b-072
 
 ### Updates
 
+#### v0.1.9
+- switched to torch.multiprocessing
+- added compute_type, input_device_index and gpu_device_index parameters
+- recorder.text() interruptable with recorder.abort()
+- fix for #20
+
+#### v0.1.8
+- added [example](https://github.com/KoljaB/RealtimeSTT/tree/master/example_browserclient) how to realtime transcribe from browser microphone
+- large-v3 whisper model now supported (upgrade to faster_whisper 0.10.0)
+- added feed_audio() and use_microphone parameter to feed chunks
+
 #### v0.1.7
 - Bugfix for Mac OS Installation (multiprocessing / queue.size())
 - KeyboardInterrupt handling (now abortable with CTRL+C)
@@ -47,7 +59,6 @@ https://github.com/KoljaB/RealtimeSTT/assets/7604638/207cb9a2-4482-48e7-9d2b-072
 - Bugfix for resource management in shutdown method
 
 #### v0.1.5
-
 - Bugfix for detection of short speech right after sentence detection (the problem mentioned in the video)
 - Main transcription and recording moved into separate process contexts with multiprocessing
 
@@ -96,7 +107,7 @@ To use RealtimeSTT with GPU support via CUDA please follow these steps:
 
 1. **Install NVIDIA CUDA Toolkit 11.8**:
     - Visit [NVIDIA CUDA Toolkit Archive](https://developer.nvidia.com/cuda-11-8-0-download-archive).
-    - Select version 11.
+    - Select operating system and version.
     - Download and install the software.
 
 2. **Install NVIDIA cuDNN 8.7.0 for CUDA 11.x**:
@@ -200,6 +211,14 @@ recorder = AudioToTextRecorder(on_recording_start=my_start_callback,
                                on_recording_stop=my_stop_callback)
 ```
 
+### Feed chunks
+
+If you don't want to use the local microphone set use_microphone parameter to false and provide raw PCM audiochunks in 16-bit mono (samplerate 16000) with this method:
+
+```python
+recorder.feed_audio(audio_chunk)
+```
+
 ### Shutdown
 
 You can shutdown the recorder safely by using the context manager protocol:
@@ -261,7 +280,13 @@ When you initialize the `AudioToTextRecorder` class, you have various options to
     - Options: 'tiny', 'tiny.en', 'base', 'base.en', 'small', 'small.en', 'medium', 'medium.en', 'large-v1', 'large-v2'.
     - Note: If a size is provided, the model will be downloaded from the Hugging Face Hub.
 
-- **language** (str, default=""): Language code for transcription. If left empty, the model will try to auto-detect the language.
+- **language** (str, default=""): Language code for transcription. If left empty, the model will try to auto-detect the language. Supported language codes are listed in [Whisper Tokenizer library](https://github.com/openai/whisper/blob/main/whisper/tokenizer.py).
+
+- **compute_type** (str, default="default"): Specifies the type of computation to be used for transcription. See [Whisper Quantization](https://opennmt.net/CTranslate2/quantization.html)
+
+- **input_device_index** (int, default=0): Audio Input Device Index to use.
+
+- **gpu_device_index** (int, default=0): GPU Device Index to use. The model can also be loaded on multiple GPUs by passing a list of IDs (e.g. [0, 1, 2, 3]).
 
 - **on_recording_start**: A callable function triggered when recording starts.
 
@@ -273,6 +298,8 @@ When you initialize the `AudioToTextRecorder` class, you have various options to
 
 - **ensure_sentence_ends_with_period** (bool, default=True): Ensures that every sentence that doesn't end with punctuation such as "?", "!" ends with a period
 
+- **use_microphone** (bool, default=True): Usage of local microphone for transcription. Set to False if you want to provide chunks with feed_audio method.
+
 - **spinner** (bool, default=True): Provides a spinner animation text with information about the current recorder state.
 
 - **level** (int, default=logging.WARNING): Logging level.

RealTimeSTT-0.1.7/PKG-INFO → RealTimeSTT-0.1.9/README.md

@@ -1,24 +1,3 @@
-Metadata-Version: 2.1
-Name: RealTimeSTT
-Version: 0.1.7
-Summary: A fast Voice Activity Detection and Transcription System
-Home-page: https://github.com/KoljaB/RealTimeSTT
-Author: Kolja Beigel
-Author-email: kolja.beigel@web.de
-Keywords: real-time,audio,transcription,speech-to-text,voice-activity-detection,VAD,real-time-transcription,ambient-noise-detection,microphone-input,faster_whisper,speech-recognition,voice-assistants,audio-processing,buffered-transcription,pyaudio,ambient-noise-level,voice-deactivity
-Classifier: Programming Language :: Python :: 3
-Classifier: License :: OSI Approved :: MIT License
-Classifier: Operating System :: OS Independent
-Requires-Python: >=3.6
-Description-Content-Type: text/markdown
-Requires-Dist: PyAudio>=0.2.13
-Requires-Dist: faster-whisper>=0.7.1
-Requires-Dist: pvporcupine==1.9.5
-Requires-Dist: webrtcvad>=2.0.10
-Requires-Dist: halo>=0.0.31
-Requires-Dist: torch>=2.0.1
-Requires-Dist: torchaudio>=2.0.2
-
 
 # RealtimeSTT
 
@@ -37,6 +16,17 @@ https://github.com/KoljaB/RealtimeSTT/assets/7604638/207cb9a2-4482-48e7-9d2b-072
 
 ### Updates
 
+#### v0.1.9
+- switched to torch.multiprocessing
+- added compute_type, input_device_index and gpu_device_index parameters
+- recorder.text() interruptable with recorder.abort()
+- fix for #20
+
+#### v0.1.8
+- added [example](https://github.com/KoljaB/RealtimeSTT/tree/master/example_browserclient) how to realtime transcribe from browser microphone
+- large-v3 whisper model now supported (upgrade to faster_whisper 0.10.0)
+- added feed_audio() and use_microphone parameter to feed chunks
+
 #### v0.1.7
 - Bugfix for Mac OS Installation (multiprocessing / queue.size())
 - KeyboardInterrupt handling (now abortable with CTRL+C)
@@ -47,7 +37,6 @@ https://github.com/KoljaB/RealtimeSTT/assets/7604638/207cb9a2-4482-48e7-9d2b-072
 - Bugfix for resource management in shutdown method
 
 #### v0.1.5
-
 - Bugfix for detection of short speech right after sentence detection (the problem mentioned in the video)
 - Main transcription and recording moved into separate process contexts with multiprocessing
 
@@ -96,7 +85,7 @@ To use RealtimeSTT with GPU support via CUDA please follow these steps:
 
 1. **Install NVIDIA CUDA Toolkit 11.8**:
     - Visit [NVIDIA CUDA Toolkit Archive](https://developer.nvidia.com/cuda-11-8-0-download-archive).
-    - Select version 11.
+    - Select operating system and version.
     - Download and install the software.
 
 2. **Install NVIDIA cuDNN 8.7.0 for CUDA 11.x**:
@@ -200,6 +189,14 @@ recorder = AudioToTextRecorder(on_recording_start=my_start_callback,
                                on_recording_stop=my_stop_callback)
 ```
 
+### Feed chunks
+
+If you don't want to use the local microphone set use_microphone parameter to false and provide raw PCM audiochunks in 16-bit mono (samplerate 16000) with this method:
+
+```python
+recorder.feed_audio(audio_chunk)
+```
+
 ### Shutdown
 
 You can shutdown the recorder safely by using the context manager protocol:
@@ -261,7 +258,13 @@ When you initialize the `AudioToTextRecorder` class, you have various options to
     - Options: 'tiny', 'tiny.en', 'base', 'base.en', 'small', 'small.en', 'medium', 'medium.en', 'large-v1', 'large-v2'.
     - Note: If a size is provided, the model will be downloaded from the Hugging Face Hub.
 
-- **language** (str, default=""): Language code for transcription. If left empty, the model will try to auto-detect the language.
+- **language** (str, default=""): Language code for transcription. If left empty, the model will try to auto-detect the language. Supported language codes are listed in [Whisper Tokenizer library](https://github.com/openai/whisper/blob/main/whisper/tokenizer.py).
+
+- **compute_type** (str, default="default"): Specifies the type of computation to be used for transcription. See [Whisper Quantization](https://opennmt.net/CTranslate2/quantization.html)
+
+- **input_device_index** (int, default=0): Audio Input Device Index to use.
+
+- **gpu_device_index** (int, default=0): GPU Device Index to use. The model can also be loaded on multiple GPUs by passing a list of IDs (e.g. [0, 1, 2, 3]).
 
 - **on_recording_start**: A callable function triggered when recording starts.
 
@@ -273,6 +276,8 @@ When you initialize the `AudioToTextRecorder` class, you have various options to
 
 - **ensure_sentence_ends_with_period** (bool, default=True): Ensures that every sentence that doesn't end with punctuation such as "?", "!" ends with a period
 
+- **use_microphone** (bool, default=True): Usage of local microphone for transcription. Set to False if you want to provide chunks with feed_audio method.
+
 - **spinner** (bool, default=True): Provides a spinner animation text with information about the current recorder state.
 
 - **level** (int, default=logging.WARNING): Logging level.
@@ -343,4 +348,4 @@ MIT
 
 Kolja Beigel  
 Email: kolja.beigel@web.de  
-[GitHub](https://github.com/KoljaB/RealtimeSTT)
+[GitHub](https://github.com/KoljaB/RealtimeSTT)

RealTimeSTT-0.1.7/README.md → RealTimeSTT-0.1.9/RealTimeSTT.egg-info/PKG-INFO

@@ -1,3 +1,25 @@
+Metadata-Version: 2.1
+Name: RealTimeSTT
+Version: 0.1.9
+Summary: A fast Voice Activity Detection and Transcription System
+Home-page: https://github.com/KoljaB/RealTimeSTT
+Author: Kolja Beigel
+Author-email: kolja.beigel@web.de
+Keywords: real-time,audio,transcription,speech-to-text,voice-activity-detection,VAD,real-time-transcription,ambient-noise-detection,microphone-input,faster_whisper,speech-recognition,voice-assistants,audio-processing,buffered-transcription,pyaudio,ambient-noise-level,voice-deactivity
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+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==0.10.0
+Requires-Dist: pvporcupine==1.9.5
+Requires-Dist: webrtcvad==2.0.10
+Requires-Dist: halo==0.0.31
+Requires-Dist: torch==2.1.2
+Requires-Dist: torchaudio==2.1.2
+
 
 # RealtimeSTT
 
@@ -16,6 +38,17 @@ https://github.com/KoljaB/RealtimeSTT/assets/7604638/207cb9a2-4482-48e7-9d2b-072
 
 ### Updates
 
+#### v0.1.9
+- switched to torch.multiprocessing
+- added compute_type, input_device_index and gpu_device_index parameters
+- recorder.text() interruptable with recorder.abort()
+- fix for #20
+
+#### v0.1.8
+- added [example](https://github.com/KoljaB/RealtimeSTT/tree/master/example_browserclient) how to realtime transcribe from browser microphone
+- large-v3 whisper model now supported (upgrade to faster_whisper 0.10.0)
+- added feed_audio() and use_microphone parameter to feed chunks
+
 #### v0.1.7
 - Bugfix for Mac OS Installation (multiprocessing / queue.size())
 - KeyboardInterrupt handling (now abortable with CTRL+C)
@@ -26,7 +59,6 @@ https://github.com/KoljaB/RealtimeSTT/assets/7604638/207cb9a2-4482-48e7-9d2b-072
 - Bugfix for resource management in shutdown method
 
 #### v0.1.5
-
 - Bugfix for detection of short speech right after sentence detection (the problem mentioned in the video)
 - Main transcription and recording moved into separate process contexts with multiprocessing
 
@@ -75,7 +107,7 @@ To use RealtimeSTT with GPU support via CUDA please follow these steps:
 
 1. **Install NVIDIA CUDA Toolkit 11.8**:
     - Visit [NVIDIA CUDA Toolkit Archive](https://developer.nvidia.com/cuda-11-8-0-download-archive).
-    - Select version 11.
+    - Select operating system and version.
     - Download and install the software.
 
 2. **Install NVIDIA cuDNN 8.7.0 for CUDA 11.x**:
@@ -179,6 +211,14 @@ recorder = AudioToTextRecorder(on_recording_start=my_start_callback,
                                on_recording_stop=my_stop_callback)
 ```
 
+### Feed chunks
+
+If you don't want to use the local microphone set use_microphone parameter to false and provide raw PCM audiochunks in 16-bit mono (samplerate 16000) with this method:
+
+```python
+recorder.feed_audio(audio_chunk)
+```
+
 ### Shutdown
 
 You can shutdown the recorder safely by using the context manager protocol:
@@ -240,7 +280,13 @@ When you initialize the `AudioToTextRecorder` class, you have various options to
     - Options: 'tiny', 'tiny.en', 'base', 'base.en', 'small', 'small.en', 'medium', 'medium.en', 'large-v1', 'large-v2'.
     - Note: If a size is provided, the model will be downloaded from the Hugging Face Hub.
 
-- **language** (str, default=""): Language code for transcription. If left empty, the model will try to auto-detect the language.
+- **language** (str, default=""): Language code for transcription. If left empty, the model will try to auto-detect the language. Supported language codes are listed in [Whisper Tokenizer library](https://github.com/openai/whisper/blob/main/whisper/tokenizer.py).
+
+- **compute_type** (str, default="default"): Specifies the type of computation to be used for transcription. See [Whisper Quantization](https://opennmt.net/CTranslate2/quantization.html)
+
+- **input_device_index** (int, default=0): Audio Input Device Index to use.
+
+- **gpu_device_index** (int, default=0): GPU Device Index to use. The model can also be loaded on multiple GPUs by passing a list of IDs (e.g. [0, 1, 2, 3]).
 
 - **on_recording_start**: A callable function triggered when recording starts.
 
@@ -252,6 +298,8 @@ When you initialize the `AudioToTextRecorder` class, you have various options to
 
 - **ensure_sentence_ends_with_period** (bool, default=True): Ensures that every sentence that doesn't end with punctuation such as "?", "!" ends with a period
 
+- **use_microphone** (bool, default=True): Usage of local microphone for transcription. Set to False if you want to provide chunks with feed_audio method.
+
 - **spinner** (bool, default=True): Provides a spinner animation text with information about the current recorder state.
 
 - **level** (int, default=logging.WARNING): Logging level.
@@ -322,4 +370,4 @@ MIT
 
 Kolja Beigel  
 Email: kolja.beigel@web.de  
-[GitHub](https://github.com/KoljaB/RealtimeSTT)
+[GitHub](https://github.com/KoljaB/RealtimeSTT)

{RealTimeSTT-0.1.7 → RealTimeSTT-0.1.9}/RealTimeSTT.egg-info/SOURCES.txt

@@ -1,3 +1,4 @@
+LICENSE
 README.md
 setup.py
 RealTimeSTT.egg-info/PKG-INFO

RealTimeSTT-0.1.9/RealTimeSTT.egg-info/requires.txt

@@ -0,0 +1,7 @@
+PyAudio==0.2.14
+faster-whisper==0.10.0
+pvporcupine==1.9.5
+webrtcvad==2.0.10
+halo==0.0.31
+torch==2.1.2
+torchaudio==2.1.2