Merge pull request #6 from nvidia-riva/release/0.0.3

Release/0.0.3

Author: PeganovAnton

.gitignore

@@ -62,12 +62,8 @@ __pycache__/
 *.py[cod]
 *$py.class
 
-# C extensions
-*.so
-
 # Distribution / packaging
 .Python
-riva/
 build/
 develop-eggs/
 dist/
@@ -187,3 +183,6 @@ tests/integration/asr/outputs
 tests/integration/nlp/outputs
 tests/integration/tts/outputs
 
+riva/client/proto/*_pb2.py
+riva/client/proto/*_pb2_grpc.py
+

README.md

@@ -6,9 +6,9 @@ case and deliver real-time performance. This repo provides performant client exa
 
 ## Main API
 
-- `riva_api.ASRService` is a class for speech recognition,
-- `riva_api.TTSService` is a class for speech synthesis,
-- `riva_api.NLPService` is a class for natural language processing.
+- `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
 
@@ -43,12 +43,12 @@ pip install --force-reinstall dist/*.whl
 ```
 3. `pip`:
 ```bash
-pip install riva-api
+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` or module 
-`riva_api/audio_io.py`), you will need to install `PyAudio`.
+`riva.client/audio_io.py`), you will need to install `PyAudio`.
 ```bash
 conda install -c anaconda pyaudio
 ```

riva_api/__init__.py renamed to riva/client/__init__.py

@@ -1,7 +1,7 @@
 # SPDX-FileCopyrightText: Copyright (c) 2022 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
 # SPDX-License-Identifier: MIT
 
-from riva_api.asr import (
+from riva.client.asr import (
     AudioChunkFileIterator,
     ASRService,
     add_audio_file_specs_to_config,
@@ -11,15 +11,15 @@
     print_streaming,
     sleep_audio_length,
 )
-from riva_api.auth import Auth
-from riva_api.nlp import (
+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_api.package_info import (
+from riva.client.package_info import (
     __contact_emails__,
     __contact_names__,
     __description__,
@@ -32,6 +32,7 @@
     __shortversion__,
     __version__,
 )
-from riva_api.proto.riva_audio_pb2 import AudioEncoding
-from riva_api.proto.riva_asr_pb2 import RecognitionConfig, StreamingRecognitionConfig
-from riva_api.tts import SpeechSynthesisService
+from riva.client.proto.riva_asr_pb2 import RecognitionConfig, StreamingRecognitionConfig
+from riva.client.proto.riva_audio_pb2 import AudioEncoding
+from riva.client.proto.riva_nlp_pb2 import AnalyzeIntentOptions
+from riva.client.tts import SpeechSynthesisService

riva_api/argparse_utils.py renamed to riva/client/argparse_utils.py

@@ -6,14 +6,15 @@
 import sys
 import time
 import warnings
+import wave
 from pathlib import Path
 from typing import Callable, Dict, Generator, Iterable, List, Optional, TextIO, Union
 
-import wave
+from grpc._channel import _MultiThreadedRendezvous
 
-import riva_api.proto.riva_asr_pb2 as rasr
-import riva_api.proto.riva_asr_pb2_grpc as rasr_srv
-from riva_api.auth import Auth
+import riva.client.proto.riva_asr_pb2 as rasr
+import riva.client.proto.riva_asr_pb2_grpc as rasr_srv
+from riva.client.auth import Auth
 
 
 def get_wav_file_parameters(input_file: Union[str, os.PathLike]) -> Dict[str, Union[int, float]]:
@@ -113,7 +114,7 @@ def print_streaming(
     Prints streaming speech recognition results to provided files or streams.
 
     Args:
-        responses (:obj:`Iterable[riva_api.proto.riva_asr_pb2.StreamingRecognizeResponse]`): responses acquired during
+        responses (:obj:`Iterable[riva.client.proto.riva_asr_pb2.StreamingRecognizeResponse]`): responses acquired during
             streaming speech recognition.
         output_file (:obj:`Union[Union[os.PathLike, str, TextIO], List[Union[os.PathLike, str, TextIO]]]`, `optional`):
             a path to an output file or a text stream or a list of paths/streams. If contains several elements, then
@@ -260,7 +261,7 @@ def __init__(self, auth: Auth) -> None:
         Initializes an instance of the class.
 
         Args:
-            auth (:obj:`riva_api.auth.Auth`): an instance of :class:`riva_api.auth.Auth` which is used for
+            auth (:obj:`riva.client.auth.Auth`): an instance of :class:`riva.client.auth.Auth` which is used for
                 authentication metadata generation.
         """
         self.auth = auth
@@ -286,28 +287,32 @@ def streaming_response_generator(
                     with wave.open(file_name, 'rb') as wav_f:
                         raw_audio = wav_f.readframes(n_frames)
 
-            streaming_config (:obj:`riva_api.proto.riva_asr_pb2.StreamingRecognitionConfig`): a config for streaming.
+            streaming_config (:obj:`riva.client.proto.riva_asr_pb2.StreamingRecognitionConfig`): a config for streaming.
                 You may find description of config fields in message ``StreamingRecognitionConfig`` in
-                `common repo <https://docs.nvidia.com/deeplearning/riva/user-guide/docs/reference/protos/protos.html#riva-proto-riva-asr-proto>`_.
+                `common repo
+                <https://docs.nvidia.com/deeplearning/riva/user-guide/docs/reference/protos/protos.html#riva-proto-riva-asr-proto>`_.
                 An example of creation of streaming config:
 
                 .. code-style:: python
 
-                    from riva_api import RecognitionConfig, StreamingRecognitionConfig
+                    from riva.client import RecognitionConfig, StreamingRecognitionConfig
                     config = RecognitionConfig(enable_automatic_punctuation=True)
                     streaming_config = StreamingRecognitionConfig(config, interim_results=True)
 
         Yields:
-            :obj:`riva_api.proto.riva_asr_pb2.StreamingRecognizeResponse`: responses for audio chunks in
+            :obj:`riva.client.proto.riva_asr_pb2.StreamingRecognizeResponse`: responses for audio chunks in
             :param:`audio_chunks`. You may find description of response fields in declaration of
             ``StreamingRecognizeResponse``
-            message `here <https://docs.nvidia.com/deeplearning/riva/user-guide/docs/reference/protos/protos.html#riva-proto-riva-asr-proto>`_.
+            message `here
+            <https://docs.nvidia.com/deeplearning/riva/user-guide/docs/reference/protos/protos.html#riva-proto-riva-asr-proto>`_.
         """
         generator = streaming_request_generator(audio_chunks, streaming_config)
         for response in self.stub.StreamingRecognize(generator, metadata=self.auth.get_auth_metadata()):
             yield response
 
-    def offline_recognize(self, audio_bytes: bytes, config: rasr.RecognitionConfig) -> rasr.RecognizeResponse:
+    def offline_recognize(
+        self, audio_bytes: bytes, config: rasr.RecognitionConfig, future: bool = False
+    ) -> Union[rasr.RecognizeResponse, _MultiThreadedRendezvous]:
         """
         Performs speech recognition for raw audio in :param:`audio_bytes`. This method is for processing of
         huge audio at once - not as it is being generated.
@@ -321,21 +326,27 @@ def offline_recognize(self, audio_bytes: bytes, config: rasr.RecognitionConfig)
                     with wave.open(file_name, 'rb') as wav_f:
                         raw_audio = wav_f.readframes(n_frames)
 
-            config (:obj:`riva_api.proto.riva_asr_pb2.RecognitionConfig`): a config for offline speech recognition.
+            config (:obj:`riva.client.proto.riva_asr_pb2.RecognitionConfig`): a config for offline speech recognition.
                 You may find description of config fields in message ``RecognitionConfig`` in
-                `common repo <https://docs.nvidia.com/deeplearning/riva/user-guide/docs/reference/protos/protos.html#riva-proto-riva-asr-proto>`_.
+                `common repo
+                <https://docs.nvidia.com/deeplearning/riva/user-guide/docs/reference/protos/protos.html#riva-proto-riva-asr-proto>`_.
                 An example of creation of config:
 
                 .. code-style:: python
 
-                    from riva_api import RecognitionConfig
+                    from riva.client import RecognitionConfig
                     config = RecognitionConfig(enable_automatic_punctuation=True)
+            future (:obj:`bool`, defaults to :obj:`False`): whether to return an async result instead of usual
+                response. You can get a response by calling ``result()`` method of the future object.
 
         Returns:
-            :obj:`riva_api.proto.riva_asr_pb2.RecognizeResponse`: a response with results of :param:`audio_bytes`
-            processing. You may find description of response fields in declaration of ``RecognizeResponse``
-            message `here <https://docs.nvidia.com/deeplearning/riva/user-guide/docs/reference/protos/protos.html#riva-proto-riva-asr-proto>`_.
+            :obj:`Union[riva.client.proto.riva_asr_pb2.RecognizeResponse, grpc._channel._MultiThreadedRendezvous]``: a
+            response with results of :param:`audio_bytes` processing. You may find description of response fields in
+            declaration of ``RecognizeResponse`` message `here
+            <https://docs.nvidia.com/deeplearning/riva/user-guide/docs/reference/protos/protos.html#riva-proto-riva-asr-proto>`_.
+            If :param:`future` is :obj:`True`, then a future object is returned. You may retrieve a response from a
+            future object by calling ``result()`` method.
         """
         request = rasr.RecognizeRequest(config=config, audio=audio_bytes)
-        response = self.stub.Recognize(request, metadata=self.auth.get_auth_metadata())
-        return response
+        func = self.stub.Recognize.future if future else self.stub.Recognize
+        return func(request, metadata=self.auth.get_auth_metadata())