nvidia-riva-client 2.22.0__2-py3-none-any.whl

nvidia_riva_client-2.22.0.dist-info/METADATA

@@ -0,0 +1,413 @@
+Metadata-Version: 2.4
+Name: nvidia-riva-client
+Version: 2.22.0
+Summary: Python implementation of the Riva Client API
+Home-page: https://github.com/nvidia-riva/python-clients
+Author: Anton Peganov
+Author-email: apeganov@nvidia.com
+Maintainer: Anton Peganov
+Maintainer-email: apeganov@nvidia.com
+License: MIT
+Keywords: deep learning,machine learning,gpu,NLP,ASR,TTS,NMT,nvidia,speech,language,Riva,client
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Programming Language :: Python :: 3
+Requires-Python: >=3.7
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: setuptools==78.1.1
+Requires-Dist: grpcio==1.67.1
+Requires-Dist: grpcio-tools==1.67.1
+Requires-Dist: websockets==15.0.1
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: keywords
+Dynamic: license
+Dynamic: license-file
+Dynamic: maintainer
+Dynamic: maintainer-email
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
+
+[![License](https://img.shields.io/badge/license-MIT-green)](https://opensource.org/licenses/MIT)
+# NVIDIA Riva Clients
+
+NVIDIA Riva is a GPU-accelerated SDK for building Speech AI applications that are customized for your use 
+case and deliver real-time performance. This repo provides performant client example command-line clients.
+
+## Main API
+
+- `riva.client.ASRService` is a class for speech recognition,
+- `riva.client.TTSService` is a class for speech synthesis,
+- `riva.client.NLPService` is a class for natural language processing.
+
+## CLI interface
+
+- **Automatic Speech Recognition (ASR)**
+    - `scripts/asr/riva_streaming_asr_client.py` demonstrates streaming transcription in several threads, can prints time stamps.
+    - `scripts/asr/transcribe_file.py` performs streaming transcription,
+    - `scripts/asr/transcribe_file_offline.py` performs offline transcription,
+    - `scripts/asr/transcribe_mic.py` performs streaming transcription of audio acquired through microphone.
+    - `scripts/asr/realtime_asr_client.py` performs realtime transcription of audio via WebSocket connection.
+- **Speech Synthesis (TTS)**
+    - `scripts/tts/talk.py` synthesizes audio for a text in streaming or offline mode.
+- **Natural Language Processing (NLP)**
+    - `scripts/nlp/intentslot_client.py` recognizes intents and slots in input sentences,
+    - `scripts/nlp/ner_client.py` detects named entities in input sentences,
+    - `scripts/nlp/punctuation_client.py` restores punctuation and capitalization in input sentences,
+    - `scripts/nlp/qa_client.py` queries a document with natural language query and prints answer from a document,
+    - `scripts/nlp/text_classify_client.py` classifies input sentences,
+    - `scripts/nlp/eval_intent_slot.py` prints intents and slots classification reports for test data.
+  
+## Installation
+
+1. Create a ``conda`` environment and activate it
+2. From source: 
+    - Clone ``riva-python-clients`` repo and change to the repo root
+    - Run commands
+
+```bash
+git clone https://github.com/nvidia-riva/python-clients.git
+cd python-clients
+git submodule init
+git submodule update --remote --recursive
+pip install -r requirements.txt
+python3 setup.py bdist_wheel
+pip install --force-reinstall dist/*.whl
+```
+3. `pip`:
+```bash
+pip install nvidia-riva-client
+```
+
+If you would like to use output and input audio devices 
+(scripts `scripts/asr/transcribe_file_rt.py`, `scripts/asr/transcribe_mic.py`, `scripts/tts/talk.py`, `scripts/asr/realtime_asr_client.py` or module 
+`riva.client/audio_io.py`), you will need to install `PyAudio`.
+```bash
+conda install -c anaconda pyaudio
+```
+
+If you would like to use Realtime ASR (WebSocket-based real-time transcription) script `scripts/asr/realtime_asr_client.py`, you will need the following dependencies:
+```bash
+conda install -c anaconda numpy 
+conda install -c anaconda requests
+conda install -c anaconda websockets
+```
+
+For NLP evaluation you will need `transformers` and `sklearn` libraries.
+```bash
+pip install -U scikit-learn
+pip install -U transformers
+```
+
+## Before using microphone and audio output devices on Unix
+you may need to run commands
+```
+adduser $USER audio
+adduser $USER pulse-access
+```
+and restart.
+
+## Usage
+
+### Server
+
+Before running client part of Riva, please set up a server. The simplest
+way to do this is to follow
+[quick start guide](https://docs.nvidia.com/deeplearning/riva/user-guide/docs/quick-start-guide.html#local-deployment-using-quick-start-scripts).
+
+### CLI
+
+You may find all CLI scripts in `scripts` directory. Each script has a description of
+its purpose and parameters.
+
+#### ASR
+
+You may find a detailed documentation [here](https://docs.nvidia.com/deeplearning/riva/user-guide/docs/apis/cli.html).
+
+For transcribing in streaming mode you may use `scripts/asr/transcribe_file.py`.
+```bash
+python scripts/asr/transcribe_file.py \
+    --input-file data/examples/en-US_AntiBERTa_for_word_boosting_testing.wav
+```
+
+You may watch how a transcript grows if you set `--simulate-realtime` and `--show-intermediate`.
+```bash
+python scripts/asr/transcribe_file.py \
+    --input-file data/examples/en-US_AntiBERTa_for_word_boosting_testing.wav \
+    --simulate-realtime \
+    --show-intermediate
+```
+
+You may listen audio simultaneously with transcribing (you will need installed PyAudio and access to audio devices).
+```bash
+python scripts/asr/transcribe_file.py \
+    --input-file data/examples/en-US_AntiBERTa_for_word_boosting_testing.wav \
+    --play-audio \
+    --show-intermediate
+```
+
+Offline transcription is performed this way.
+```bash
+python scripts/asr/transcribe_file_offline.py \
+    --input-file data/examples/en-US_AntiBERTa_for_word_boosting_testing.wav
+```
+
+You can improve transcription of this audio by word boosting.
+```bash
+python scripts/asr/transcribe_file_offline.py \
+  --input-file data/examples/en-US_AntiBERTa_for_word_boosting_testing.wav \
+  --boosted-lm-words AntiBERTa \
+  --boosted-lm-words ABlooper \
+  --boosted-lm-score 20.0
+```
+
+For transcribing in realtime mode you may use `scripts/asr/realtime_asr_client.py`.
+
+**From audio file:**
+```bash
+python scripts/asr/realtime_asr_client.py \
+  --input-file data/examples/en-US_AntiBERTa_for_word_boosting_testing.wav
+```
+
+**From microphone:**
+```bash
+python scripts/asr/realtime_asr_client.py \
+  --mic \
+  --duration 30 \
+  --output-text transcript.txt
+```
+
+**List available audio devices:**
+```bash
+python scripts/asr/realtime_asr_client.py --list-devices
+```
+
+**Use specific audio device:**
+```bash
+python scripts/asr/realtime_asr_client.py \
+  --mic \
+  --input-device 1 \
+  --duration 30 \
+  --output-text transcript.txt
+```
+
+For **WebSocket-based Realtime Transcription** (using `riva.client.realtime.RealtimeClient`), you can transcribe audio files or microphone input with real-time results:
+
+**From audio file:**
+```python
+from riva.client.realtime import RealtimeClient
+from riva.client.asr import AudioChunkFileIterator
+import asyncio
+import argparse
+
+async def transcribe_file():
+    # Create arguments namespace
+    args = argparse.Namespace()
+    args.input_file = "path/to/audio.wav"  # Required for file input
+    args.mic = False  # Set to True for microphone input
+    args.server = "localhost:9090"
+    args.endpoint = "/v1/realtime"
+    args.query_params = "intent=transcription"
+    args.sample_rate_hz = 16000
+    args.num_channels = 1
+    args.file_streaming_chunk = 1600
+    args.output_text = "transcript.txt"
+    args.prompt = ""
+    args.language_code = "en-US"
+    args.model_name = ""
+    args.automatic_punctuation = False
+    args.no_verbatim_transcripts = False
+    args.profanity_filter = False
+    args.word_time_offsets = False
+    args.max_alternatives = 1
+    args.boosted_lm_words = []
+    args.boosted_lm_score = 4.0
+    args.speaker_diarization = False
+    args.diarization_max_speakers = 3
+    args.start_history = -1
+    args.start_threshold = -1.0
+    args.stop_history = -1
+    args.stop_threshold = -1.0
+    args.stop_history_eou = -1
+    args.stop_threshold_eou = -1.0
+    args.custom_configuration = ""
+    
+    client = RealtimeClient(args=args)
+    
+    await client.connect()
+    
+    # Create audio iterator
+    audio_chunk_iterator = AudioChunkFileIterator(
+        args.input_file, 
+        args.file_streaming_chunk, 
+        delay_callback=None
+    )
+    
+    # Send audio and receive responses concurrently
+    await asyncio.gather(
+        client.send_audio_chunks(audio_chunk_iterator),
+        client.receive_responses()
+    )
+    
+    client.save_responses("transcript.txt")
+    await client.disconnect()
+
+asyncio.run(transcribe_file())
+```
+
+**From microphone:**
+```python
+from riva.client.realtime import RealtimeClient
+from riva.client.audio_io import MicrophoneStream
+import asyncio
+import argparse
+
+async def transcribe_microphone():
+    # Create arguments namespace
+    args = argparse.Namespace()
+    args.input_file = None  # Not needed for microphone input
+    args.mic = True
+    args.duration = 30  # 30 seconds
+    args.input_device = None  # Use default device
+    args.server = "localhost:9090"
+    args.endpoint = "/v1/realtime"
+    args.query_params = "intent=transcription"
+    args.sample_rate_hz = 16000
+    args.num_channels = 1
+    args.file_streaming_chunk = 1600
+    args.output_text = "transcript.txt"
+    args.prompt = ""
+    args.language_code = "en-US"
+    args.model_name = ""
+    args.automatic_punctuation = False
+    args.no_verbatim_transcripts = False
+    args.profanity_filter = False
+    args.word_time_offsets = False
+    args.max_alternatives = 1
+    args.boosted_lm_words = []
+    args.boosted_lm_score = 4.0
+    args.speaker_diarization = False
+    args.diarization_max_speakers = 3
+    args.start_history = -1
+    args.start_threshold = -1.0
+    args.stop_history = -1
+    args.stop_threshold = -1.0
+    args.stop_history_eou = -1
+    args.stop_threshold_eou = -1.0
+    args.custom_configuration = ""
+    
+    client = RealtimeClient(args=args)
+    
+    await client.connect()
+    
+    # Create microphone stream
+    mic_chunks = MicrophoneStream(
+        args.sample_rate_hz, 
+        args.file_streaming_chunk, 
+        device=None
+    )
+    
+    await asyncio.gather(
+        client.send_audio_chunks(mic_chunks),
+        client.receive_responses()
+    )
+    
+    await client.disconnect()
+
+asyncio.run(transcribe_microphone())
+```
+
+#### NLP
+
+You can provide inputs to `scripts/nlp/intentslot_client.py`, `scripts/nlp/punctuation_client.py`
+both through command line arguments and interactively.
+```bash
+python scripts/nlp/intentslot_client.py --query "What is the weather tomorrow?"
+```
+or
+```bash
+python scripts/nlp/intentslot_client.py --interactive
+```
+For punctuation client the commands look similar.
+```bash
+python scripts/nlp/punctuation_client.py --query "can you prove that you are self aware"
+```
+or
+```bash
+python scripts/nlp/punctuation_client.py --interactive
+```
+
+**NER** client can output 1 of the following: label name, span start, span end
+```bash
+python scripts/nlp/ner_client.py \
+  --query "Where is San Francisco?" "Jensen Huang is the CEO of NVIDIA Corporation." \
+  --test label
+```
+or
+```bash
+python scripts/nlp/ner_client.py \
+  --query "Where is San Francisco?" "Jensen Huang is the CEO of NVIDIA Corporation." \
+  --test span_start
+```
+or
+```bash
+python scripts/nlp/ner_client.py \
+  --query "Where is San Francisco?" "Jensen Huang is the CEO of NVIDIA Corporation." \
+  --test span_end
+```
+
+Provide query and context to **QA** client.
+```bash
+python scripts/nlp/qa_client.py \
+  --query "How many gigatons of carbon dioxide was released in 2005?" \
+  --context "In 2010 the Amazon rainforest experienced another severe drought, in some ways "\
+"more extreme than the 2005 drought. The affected region was approximate 1,160,000 square "\
+"miles (3,000,000 km2) of rainforest, compared to 734,000 square miles (1,900,000 km2) in "\
+"2005. The 2010 drought had three epicenters where vegetation died off, whereas in 2005 the "\
+"drought was focused on the southwestern part. The findings were published in the journal "\
+"Science. In a typical year the Amazon absorbs 1.5 gigatons of carbon dioxide; during 2005 "\
+"instead 5 gigatons were released and in 2010 8 gigatons were released."
+```
+
+**Text classification** requires only a query.
+```bash
+python scripts/nlp/text_classify_client.py --query "How much sun does california get?"
+```
+
+#### TTS
+
+Call ``scripts/tts/talk.py`` script, and you will be prompted to enter a text for speech
+synthesis. Set `--play-audio` option, and a synthesized speech will be played.
+```bash
+python scripts/tts/talk.py --play-audio
+```
+
+You can write output to file.
+```bash
+python scripts/tts/talk.py --output 'my_synth_speech.wav'
+```
+
+You can use streaming mode (audio fragments returned to client as soon as they are ready).
+```bash
+python scripts/tts/talk.py --stream --play-audio
+```
+
+### API
+
+See tutorial notebooks in directory `tutorials`.
+
+
+## Documentation
+
+Additional documentation on the Riva Speech Skills SDK can be found [here](https://docs.nvidia.com/deeplearning/riva/user-guide/docs/).
+
+
+## License
+
+This client code is MIT-licensed. See LICENSE file for full details.

nvidia_riva_client-2.22.0.dist-info/RECORD

@@ -0,0 +1,31 @@
+nvidia_riva_client-2.22.0.dist-info/licenses/LICENSE,sha256=nAu1MzYxnBPQYaIkbupPPyFrrTHN6x_J_w_Y2DCN1UM,1096
+riva/client/__init__.py,sha256=kmu7kS7D7Vjb-HCNdD0_fsfBCJ-I7c0cjt2a6bf1bmg,1551
+riva/client/argparse_utils.py,sha256=Jnhy6CtkvDvRdR-CxQvKakXzM7NiNlbdN7yDcp9On1s,5701
+riva/client/asr.py,sha256=r1HzJtz7kjvjfRSJDtuZ6ndA0R4sHCdclx8CLjU6ntk,22641
+riva/client/audio_io.py,sha256=IxarMvzYaXFZjao-rPaJI31BpwW4REn8jc7aQ71o_Cg,4080
+riva/client/auth.py,sha256=xTS--xLjApscPISvDAyVAqUonljMihFOFuGDEchWdX4,6454
+riva/client/health.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+riva/client/nlp.py,sha256=LXsEzVMwO7qWFMH4eOFQTmtXevuCKxzRRs28KtWIWdA,20537
+riva/client/nmt.py,sha256=S3nATJEAhveMTJAnrV38Uw4zT_q0GREbJOajGOHUR7Q,9797
+riva/client/package_info.py,sha256=WHnd0GXw_RwZKhCaUQHV8T5Jc-4Jw2BH_8inBdAlS6U,1021
+riva/client/realtime.py,sha256=vde-EE0O-RKR3b9LksYIVdLriN7YJEd6ep1tksnanIM,20891
+riva/client/tts.py,sha256=K5BZTImzlfHwQBw8GoD6VIbz6a8a9T6RlJ9Osg5cQRc,8048
+riva/client/proto/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+riva/client/proto/health_pb2.py,sha256=sAkbVqOwmqm6H3s05XUWcUHgEi_n5ak9QRNPCyMz0mE,2288
+riva/client/proto/health_pb2_grpc.py,sha256=qgd2XXHtpr5pRMSDhLgOBWvYSUOScNN94mr2ct6FvNg,5305
+riva/client/proto/riva_asr_pb2.py,sha256=bjbA18qiozA_iYL1mGKf8kQBIC0VHv25OPCEVaQA3Ks,9631
+riva/client/proto/riva_asr_pb2_grpc.py,sha256=PAgBm8aLKSqMQhPmOS2GlXcFPBxVdVXr_LTXCcNFKXg,8406
+riva/client/proto/riva_audio_pb2.py,sha256=jA1516mytkj2XYAVogH3MvGZZ27Hn0HqGw74vmkOqdE,1632
+riva/client/proto/riva_audio_pb2_grpc.py,sha256=7AA923pFme4iIfQ1gbgeoIaefbrGrXv7A2ZjGl3nxDM,902
+riva/client/proto/riva_common_pb2.py,sha256=FDDqw1-RHZAjhe_HjiUUzivylElhTY-zwRCspD0Qrfk,1470
+riva/client/proto/riva_common_pb2_grpc.py,sha256=oJtppsuIi-V3fdHsDFSWKXme_HjE0NPygX7EmmafgXs,903
+riva/client/proto/riva_nlp_pb2.py,sha256=ctIVcfwYI0QQ1nAAR8LGZsHzRahEEbHUg_sy59Ow3vQ,19030
+riva/client/proto/riva_nlp_pb2_grpc.py,sha256=EUuyuSE1GAlBnrqgRVDUGJesJIKtzvrufkIDIbGRjzY,18887
+riva/client/proto/riva_nmt_pb2.py,sha256=laMC7_CuvXkYD10O0ayjrEmdiaPPAm67-3qyvxASm1w,7869
+riva/client/proto/riva_nmt_pb2_grpc.py,sha256=CBktyLnEZjiNXyl6tfjdN8pcXLMP8N7Lv2SNUrdKBtw,10343
+riva/client/proto/riva_tts_pb2.py,sha256=ga2biFohaQWcslv76PEOddSCNA5s1Sw1xm6hViYRBuE,4939
+riva/client/proto/riva_tts_pb2_grpc.py,sha256=IXWwdWQ4Dz_pgI5pvHPaEUcf4PEHvDKX_Sa_EVp5gxs,8017
+nvidia_riva_client-2.22.0.dist-info/METADATA,sha256=2-YmbYi8IHNxkEOvvtOZxXQsw_kBuoXqBaU_RDnewkQ,13208
+nvidia_riva_client-2.22.0.dist-info/WHEEL,sha256=lTU6B6eIfYoiQJTZNc-fyaR6BpL6ehTzU3xGYxn2n8k,91
+nvidia_riva_client-2.22.0.dist-info/top_level.txt,sha256=TkNUc1bbS7wIfdAJ4f9Y-Yh57tJoas_DdKaB0UYEA4s,5
+nvidia_riva_client-2.22.0.dist-info/RECORD,,

nvidia_riva_client-2.22.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (78.1.1)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

nvidia_riva_client-2.22.0.dist-info/licenses/LICENSE

@@ -0,0 +1,19 @@
+Copyright (c) 2022 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+
+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.

nvidia_riva_client-2.22.0.dist-info/top_level.txt

@@ -0,0 +1 @@
+riva

riva/client/__init__.py

@@ -0,0 +1,43 @@
+# SPDX-FileCopyrightText: Copyright (c) 2022 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: MIT
+
+from riva.client.asr import (
+    AudioChunkFileIterator,
+    ASRService,
+    add_audio_file_specs_to_config,
+    add_word_boosting_to_config,
+    add_speaker_diarization_to_config,
+    get_wav_file_parameters,
+    print_offline,
+    print_streaming,
+    sleep_audio_length,
+    add_endpoint_parameters_to_config,
+    add_custom_configuration_to_config,
+)
+from riva.client.auth import Auth
+from riva.client.nlp import (
+    NLPService,
+    extract_all_text_classes_and_confidences,
+    extract_all_token_classification_predictions,
+    extract_most_probable_text_class_and_confidence,
+    extract_most_probable_token_classification_predictions,
+)
+from riva.client.package_info import (
+    __contact_emails__,
+    __contact_names__,
+    __description__,
+    __download_url__,
+    __homepage__,
+    __keywords__,
+    __license__,
+    __package_name__,
+    __repository_url__,
+    __shortversion__,
+    __version__,
+)
+from riva.client.proto.riva_asr_pb2 import RecognitionConfig, StreamingRecognitionConfig, EndpointingConfig
+from riva.client.proto.riva_audio_pb2 import AudioEncoding
+from riva.client.proto.riva_nlp_pb2 import AnalyzeIntentOptions
+from riva.client.proto.riva_nmt_pb2 import StreamingTranslateSpeechToSpeechConfig, TranslationConfig, SynthesizeSpeechConfig, StreamingTranslateSpeechToTextConfig
+from riva.client.tts import SpeechSynthesisService
+from riva.client.nmt import NeuralMachineTranslationClient

riva/client/argparse_utils.py

@@ -0,0 +1,135 @@
+# SPDX-FileCopyrightText: Copyright (c) 2022 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: MIT
+
+import argparse
+
+def validate_grpc_message_size(value):
+    """Validate that the GRPC message size is within acceptable limits."""
+    min_size = 4 * 1024 * 1024  # 4MB
+    max_size = 1024 * 1024 * 1024  # 1GB
+
+    try:
+        size = int(value)
+        if size < min_size:
+            raise argparse.ArgumentTypeError(f"GRPC message size must be at least {min_size} bytes (4MB)")
+        if size > max_size:
+            raise argparse.ArgumentTypeError(f"GRPC message size must be at most {max_size} bytes (1GB)")
+        return size
+    except ValueError:
+        raise argparse.ArgumentTypeError(f"'{value}' is not a valid integer")
+
+def add_asr_config_argparse_parameters(
+    parser: argparse.ArgumentParser, max_alternatives: bool = False, profanity_filter: bool = False, word_time_offsets: bool = False
+) -> argparse.ArgumentParser:
+    if word_time_offsets:
+        parser.add_argument(
+            "--word-time-offsets", default=False, action='store_true', help="Option to output word timestamps."
+        )
+    if max_alternatives:
+        parser.add_argument(
+            "--max-alternatives",
+            default=1,
+            type=int,
+            help="Maximum number of alternative transcripts to return (up to limit configured on server).",
+        )
+    if profanity_filter:
+        parser.add_argument(
+        "--profanity-filter",
+        default=False,
+        action='store_true',
+        help="Flag that controls the profanity filtering in the generated transcripts",
+    )
+    parser.add_argument(
+        "--automatic-punctuation",
+        default=False,
+        action='store_true',
+        help="Flag that controls if transcript should be automatically punctuated",
+    )
+    parser.add_argument(
+        "--no-verbatim-transcripts",
+        default=False,
+        action='store_true',
+        help="If specified, text inverse normalization will be applied",
+    )
+    parser.add_argument("--language-code", default="en-US", help="Language code of the model to be used.")
+    parser.add_argument("--model-name", default="", help="Model name to be used.")
+    parser.add_argument("--boosted-lm-words", action='append', help="Words to boost when decoding. Can be used multiple times to boost multiple words.")
+    parser.add_argument(
+        "--boosted-lm-score", type=float, default=4.0, help="Recommended range for the boost score is 20 to 100. The higher the boost score, the more biased the ASR engine is towards this word."
+    )
+    parser.add_argument(
+        "--speaker-diarization",
+        default=False,
+        action='store_true',
+        help="Flag that controls if speaker diarization should be performed",
+    )
+    parser.add_argument(
+        "--diarization-max-speakers",
+        default=3,
+        type=int,
+        help="Max number of speakers to detect when performing speaker diarization",
+    )
+    parser.add_argument(
+        "--start-history",
+        default=-1,
+        type=int,
+        help="Value (in milliseconds) to detect and initiate start of speech utterance",
+    )
+    parser.add_argument(
+        "--start-threshold",
+        default=-1.0,
+        type=float,
+        help="Threshold value for detecting the start of speech utterance",
+    )
+    parser.add_argument(
+        "--stop-history",
+        default=-1,
+        type=int,
+        help="Value (in milliseconds) to detect end of utterance and reset decoder",
+    )
+    parser.add_argument(
+        "--stop-threshold",
+        default=-1.0,
+        type=float,
+        help="Threshold value for detecting the end of speech utterance",
+    )
+    parser.add_argument(
+        "--stop-history-eou",
+        default=-1,
+        type=int,
+        help="Value (in milliseconds) to detect end of utterance for the 1st pass and generate an intermediate final transcript",
+    )
+    parser.add_argument(
+        "--stop-threshold-eou",
+        default=-1.0,
+        type=float,
+        help="Threshold value for likelihood of blanks before detecting end of utterance",
+    )
+    parser.add_argument(
+        "--custom-configuration",
+        default="",
+        type=str,
+        help="Custom configurations to be sent to the server as key value pairs <key:value,key:value,...>",
+    )
+    return parser
+
+
+def add_connection_argparse_parameters(parser: argparse.ArgumentParser) -> argparse.ArgumentParser:
+    parser.add_argument("--server", default="localhost:50051", help="URI to GRPC server endpoint.")
+    parser.add_argument("--ssl-root-cert", help="Path to SSL root certificates file.")
+    parser.add_argument("--ssl-client-cert", help="Path to SSL client certificates file.")
+    parser.add_argument("--ssl-client-key", help="Path to SSL client key file.")
+    parser.add_argument(
+        "--use-ssl", action='store_true', help="Boolean to control if SSL/TLS encryption should be used."
+    )
+    parser.add_argument("--metadata", action='append', nargs='+', help="Send HTTP Header(s) to server")
+    parser.add_argument("--options", action='append', nargs='+', help="Send GRPC options to server")
+    parser.add_argument(
+        "--max-message-length", type=validate_grpc_message_size, default=64 * 1024 * 1024, help="Maximum message length for GRPC server."
+    )
+    return parser
+
+def add_realtime_config_argparse_parameters(parser: argparse.ArgumentParser) -> argparse.ArgumentParser:
+    parser.add_argument("--endpoint", default="/v1/realtime", help="Endpoint to WebSocket server endpoint.")
+    parser.add_argument("--query-params", default="intent=transcription", help="Query parameters to WebSocket server endpoint.")
+    return parser