phonexia-enhanced-speech-to-text-built-on-whisper-client 1.7.0__tar.gz → 1.8.0__tar.gz

{phonexia_enhanced_speech_to_text_built_on_whisper_client-1.7.0 → phonexia_enhanced_speech_to_text_built_on_whisper_client-1.8.0}/PKG-INFO

@@ -1,21 +1,22 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.3
 Name: phonexia-enhanced-speech-to-text-built-on-whisper-client
-Version: 1.7.0
+Version: 1.8.0
 Summary: Client for communication with Phonexia Enhanced Speech To Text Built On Whisper microservice.
 Keywords: grpc,transcription,STT,ASR,speech to text,speech,language,microservice
 Author: Phonexia
 Author-email: info@phonexia.com
-Requires-Python: >=3.8,<4.0
+Requires-Python: >=3.9,<4.0
 Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.8
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
 Requires-Dist: grpcio (>=1.54.0,<2.0.0)
 Requires-Dist: numpy (<2.0.0) ; python_version < "3.12"
 Requires-Dist: numpy (>=2.0.0) ; python_version >= "3.12"
 Requires-Dist: phonexia-grpc (>=2.0.0,<3.0.0)
+Requires-Dist: protobuf (>=5.0.0,<6.0.0)
 Requires-Dist: soundfile (>=0.12.1,<0.13.0)
 Project-URL: Homepage, https://phonexia.com
 Project-URL: Issues, https://phonexia.atlassian.net/servicedesk/customer/portal/15/group/20/create/40
@@ -31,6 +32,6 @@ This module contains client for communication with [enhanced speech to text buil
 
 To use this client you will first need a running instance of any *Phonexia enhanced speech to text built on whisper microservice*. If you don't yet have any running instance, don't hesitate to [contact our sales department](mailto:info@phonexia.com).
 
-You can learn more about the enhanced speech to text built on whisper technology [here](https://docs.cloud.phonexia.com/docs/category/enhanced-speech-to-text-built-on-whisper).
+You can learn more about the enhanced speech to text built on whisper technology [here](https://docs.phonexia.com/products/speech-platform-4/technologies/speech-to-text/enhanced-speech-to-text-built-on-whisper).
 
-On [this page](https://docs.cloud.phonexia.com/docs/products/speech-platform-4/grpc/api/phonexia/grpc/technologies/enhanced_speech_to_text_built_on_whisper/v1/enhanced_speech_to_text_built_on_whisper.proto), you will find a *gRPC API* reference for *enhanced speech to text built on whisper microservice*.
+On [this page](https://docs.phonexia.com/products/speech-platform-4/grpc/api/phonexia/grpc/technologies/enhanced_speech_to_text_built_on_whisper/v1/enhanced_speech_to_text_built_on_whisper.proto), you will find a *gRPC API* reference for *enhanced speech to text built on whisper microservice*.

{phonexia_enhanced_speech_to_text_built_on_whisper_client-1.7.0 → phonexia_enhanced_speech_to_text_built_on_whisper_client-1.8.0}/phonexia_enhanced_speech_to_text_built_on_whisper_client.py

@@ -45,11 +45,14 @@ def transcribe_request_iterator(
     start: Optional[float],
     end: Optional[float],
     enable_language_switching: bool = False,
+    enable_word_segmentation: bool = False,
     use_raw_audio: bool = False,
 ) -> Iterator[TranscribeRequest]:
     time_range = TimeRange(start=time_to_duration(start), end=time_to_duration(end))
     config = TranscribeConfig(
-        language=specified_language, enable_language_switching=enable_language_switching
+        language=specified_language,
+        enable_language_switching=enable_language_switching,
+        enable_word_segmentation=enable_word_segmentation,
     )
 
     if use_raw_audio:
@@ -89,10 +92,13 @@ def translate_request_iterator(
     start: Optional[float],
     end: Optional[float],
     enable_language_switching: bool = False,
+    enable_word_segmentation: bool = False,
 ) -> Iterator[TranslateRequest]:
     time_range = TimeRange(start=time_to_duration(start), end=time_to_duration(end))
     config = TranslateConfig(
-        source_language=specified_language, enable_language_switching=enable_language_switching
+        source_language=specified_language,
+        enable_language_switching=enable_language_switching,
+        enable_word_segmentation=enable_word_segmentation,
     )
 
     with open(file, "rb") as f:
@@ -111,6 +117,7 @@ def transcribe(
     metadata: Optional[list],
     task: Task,
     enable_language_switching: bool = False,
+    enable_word_segmentation: bool = False,
     use_raw_audio: bool = False,
 ):
     stub = stt_grpc.SpeechToTextStub(channel)
@@ -122,6 +129,7 @@ def transcribe(
                 start=start,
                 end=end,
                 enable_language_switching=enable_language_switching,
+                enable_word_segmentation=enable_word_segmentation,
                 use_raw_audio=use_raw_audio,
             ),
             metadata=metadata,
@@ -134,6 +142,7 @@ def transcribe(
                 start=start,
                 end=end,
                 enable_language_switching=enable_language_switching,
+                enable_word_segmentation=enable_word_segmentation,
             ),
             metadata=metadata,
         )
@@ -222,6 +231,11 @@ def main():
         action="store_true",
         help="Enable dynamic language switching during transcription, with the language being detected approximately every 30 seconds",
     )
+    parser.add_argument(
+        "--enable-word-segmentation",
+        action="store_true",
+        help="Enable word-level transcription. Note: Enabling this option may increase processing time",
+    )
     parser.add_argument("file", type=str, help="Path to input file")
     parser.add_argument("--use_raw_audio", action="store_true", help="Send a raw audio in")
 
@@ -265,6 +279,7 @@ def main():
             metadata=args.metadata,
             task=args.task,
             enable_language_switching=args.enable_language_switching,
+            enable_word_segmentation=args.enable_word_segmentation,
             use_raw_audio=args.use_raw_audio,
         )
 

{phonexia_enhanced_speech_to_text_built_on_whisper_client-1.7.0 → phonexia_enhanced_speech_to_text_built_on_whisper_client-1.8.0}/pypi-README.md

@@ -7,6 +7,6 @@ This module contains client for communication with [enhanced speech to text buil
 
 To use this client you will first need a running instance of any *Phonexia enhanced speech to text built on whisper microservice*. If you don't yet have any running instance, don't hesitate to [contact our sales department](mailto:info@phonexia.com).
 
-You can learn more about the enhanced speech to text built on whisper technology [here](https://docs.cloud.phonexia.com/docs/category/enhanced-speech-to-text-built-on-whisper).
+You can learn more about the enhanced speech to text built on whisper technology [here](https://docs.phonexia.com/products/speech-platform-4/technologies/speech-to-text/enhanced-speech-to-text-built-on-whisper).
 
-On [this page](https://docs.cloud.phonexia.com/docs/products/speech-platform-4/grpc/api/phonexia/grpc/technologies/enhanced_speech_to_text_built_on_whisper/v1/enhanced_speech_to_text_built_on_whisper.proto), you will find a *gRPC API* reference for *enhanced speech to text built on whisper microservice*.
+On [this page](https://docs.phonexia.com/products/speech-platform-4/grpc/api/phonexia/grpc/technologies/enhanced_speech_to_text_built_on_whisper/v1/enhanced_speech_to_text_built_on_whisper.proto), you will find a *gRPC API* reference for *enhanced speech to text built on whisper microservice*.

{phonexia_enhanced_speech_to_text_built_on_whisper_client-1.7.0 → phonexia_enhanced_speech_to_text_built_on_whisper_client-1.8.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "phonexia-enhanced-speech-to-text-built-on-whisper-client"
-version = "1.7.0"
+version = "1.8.0"
 description = "Client for communication with Phonexia Enhanced Speech To Text Built On Whisper microservice."
 readme = "pypi-README.md"
 keywords = ["grpc", "transcription", "STT", "ASR", "speech to text", "speech", "language", "microservice"]
@@ -15,8 +15,9 @@ protofiles = "https://github.com/phonexia/protofiles"
 enhanced_speech_to_text_built_on_whisper_client = 'phonexia_enhanced_speech_to_text_built_on_whisper_client:main'
 
 [tool.poetry.dependencies]
-python = ">=3.8,<4.0"
+python = ">=3.9,<4.0"
 grpcio = "^1.54.0"
+protobuf = "^5.0.0"
 phonexia-grpc = {version="^2.0.0", source="pypi"}
 soundfile = "^0.12.1"
 numpy = [
@@ -30,7 +31,7 @@ pytest-cov = "^5.0.0"
 pytest-env = "^1.0.0"
 pytest-random-order = "^1.1.0"
 black = "^24.0.0"
-ruff = "^0.6.0"
+ruff = "^0.8.0"
 
 [[tool.poetry.source]]
 name = "PyPI"
@@ -46,11 +47,11 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.black]
 line-length = 100
-target-version = ['py38']
+target-version = ['py39']
 preview = true
 
 [tool.ruff]
-target-version = "py38"
+target-version = "py39"
 line-length = 100
 fix = true
 lint.select = [