phonexia-enhanced-speech-to-text-built-on-whisper-client 1.2.3__tar.gz → 1.2.5__tar.gz

{phonexia_enhanced_speech_to_text_built_on_whisper_client-1.2.3 → phonexia_enhanced_speech_to_text_built_on_whisper_client-1.2.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: phonexia-enhanced-speech-to-text-built-on-whisper-client
-Version: 1.2.3
+Version: 1.2.5
 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
@@ -13,7 +13,7 @@ Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Requires-Dist: grpcio (>=1.54.0,<2.0.0)
-Requires-Dist: phonexia-grpc (>=1.0.0,<2.0.0)
+Requires-Dist: phonexia-grpc (>=2.0.0,<3.0.0)
 Project-URL: Homepage, https://phonexia.com
 Project-URL: Issues, https://phonexia.atlassian.net/servicedesk/customer/portal/15/group/20/create/40
 Project-URL: protofiles, https://github.com/phonexia/protofiles

{phonexia_enhanced_speech_to_text_built_on_whisper_client-1.2.3 → phonexia_enhanced_speech_to_text_built_on_whisper_client-1.2.5}/phonexia_enhanced_speech_to_text_built_on_whisper_client.py

@@ -1,4 +1,5 @@
 import argparse
+import json
 import logging
 import os
 from enum import Enum
@@ -6,6 +7,8 @@ from typing import Iterator, Optional
 
 import google.protobuf.duration_pb2
 import grpc
+from google.protobuf.json_format import MessageToDict
+
 import phonexia.grpc.technologies.enhanced_speech_to_text_built_on_whisper.v1.enhanced_speech_to_text_built_on_whisper_pb2_grpc as stt_grpc
 from phonexia.grpc.common.core_pb2 import Audio, TimeRange
 from phonexia.grpc.technologies.enhanced_speech_to_text_built_on_whisper.v1.enhanced_speech_to_text_built_on_whisper_pb2 import (
@@ -26,7 +29,7 @@ class Task(Enum):
         return self.value
 
 
-def time_to_duration(time: float) -> google.protobuf.duration_pb2.Duration | None:
+def time_to_duration(time: float) -> Optional[google.protobuf.duration_pb2.Duration]:
     if time is None:
         return None
     duration = google.protobuf.duration_pb2.Duration()
@@ -111,37 +114,32 @@ def transcribe(
     else:
         raise RuntimeError("Unknown task")
 
-    warning_message = []
+    info_message = []
+    response_dict = None
     for _response in response:
+        if not response_dict:
+            response_dict = MessageToDict(_response)
+        else:
+            response_dict["result"]["oneBest"]["segments"] += \
+                MessageToDict(_response)["result"]["oneBest"]["segments"]  # fmt: skip
+
         for segment in _response.result.one_best.segments:
-            print(
-                f"[{segment.start_time.ToJsonString()} -> {segment.end_time.ToJsonString()} "
-                + (
-                    f"{segment.language}"
-                    if task == Task.transcribe
-                    else f"{segment.source_language} -> {segment.language}"
-                )
-                + f"] {segment.text}"
-            )
             if segment.source_language != segment.detected_source_language:
-                warning_message.append(
-                    f"Language '{segment.detected_source_language}' was detected, but the license does not support this language. "
-                    f"Instead the segment was {'transcribed' if task == Task.transcribe else 'translated'} with the "
+                info_message.append(
+                    f"Language '{segment.detected_source_language}' was detected in the audio, but instead "
+                    f"the segment was {'transcribed' if task == Task.transcribe else 'translated'} with the "
                     + (
                         f"closest available source language '{segment.source_language}'"
                         if language is None
-                        else f"language '{language}' that was enforced by argument '--language'"
+                        else f"language '{language}' that was enforced by the '--language' argument"
                     )
-                    + ". For more info on this problem don't hesitate to contact Phonexia."
                 )
-        if _response.HasField("processed_audio_length"):
-            print(f"Processed audio length: {_response.processed_audio_length.ToJsonString()}")
-
-    warning_message = set(warning_message)
-    if len(warning_message) > 0:
-        print()
-        for warning in warning_message:
-            print(f"WARNING: {warning}")
+
+    print(json.dumps(response_dict, indent=2, ensure_ascii=False))
+    info_message = set(info_message)
+    if len(info_message) > 0:
+        for msg in info_message:
+            logging.info(msg)
 
 
 def main():

{phonexia_enhanced_speech_to_text_built_on_whisper_client-1.2.3 → phonexia_enhanced_speech_to_text_built_on_whisper_client-1.2.5}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "phonexia-enhanced-speech-to-text-built-on-whisper-client"
-version = "1.2.3"
+version = "1.2.5"
 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"]
@@ -17,7 +17,7 @@ enhanced_speech_to_text_built_on_whisper_client = 'phonexia_enhanced_speech_to_t
 [tool.poetry.dependencies]
 python = ">=3.8,<4.0"
 grpcio = "^1.54.0"
-phonexia-grpc = {version="^1.0.0", source="pypi"}
+phonexia-grpc = {version="^2.0.0", source="pypi"}
 
 [tool.poetry.group.dev.dependencies]
 pytest = "^8.0.0"
@@ -50,7 +50,7 @@ preview = true
 target-version = "py38"
 line-length = 100
 fix = true
-select = [
+lint.select = [
     # flake8-2020
     "YTT",
     # flake8-bandit
@@ -82,7 +82,7 @@ select = [
     # tryceratops
     "TRY",
 ]
-ignore = [
+lint.ignore = [
     # LineTooLong
     "E501",
     # DoNotAssignLambda