changed requirements

README.md

@@ -88,13 +88,16 @@ transcript will also indicate the timeframe in seconds where each speaker speaks
 ### Transcription example:
 
 ```
+import os
+from speechlib import Transcriptor
+
 file = "obama_zach.wav"  # your audio file
 voices_folder = "" # voices folder containing voice samples for recognition
 language = "en"          # language code
 log_folder = "logs"      # log folder for storing transcripts
 modelSize = "tiny"     # size of model to be used [tiny, small, medium, large-v1, large-v2, large-v3]
 quantization = False   # setting this 'True' may speed up the process but lower the accuracy
-ACCESS_TOKEN = "your hf key" # get permission to access pyannote/[email protected] on huggingface
+ACCESS_TOKEN = "huggingface api key" # get permission to access pyannote/[email protected] on huggingface
 
 # quantization only works on faster-whisper
 transcriptor = Transcriptor(file, log_folder, language, modelSize, ACCESS_TOKEN, voices_folder, quantization)
@@ -112,7 +115,7 @@ res = transcriptor.custom_whisper("D:/whisper_tiny_model/tiny.pt")
 res = transcriptor.huggingface_model("Jingmiao/whisper-small-chinese_base")
 
 # use assembly ai model
-res = transcriptor.assemby_ai_model("your api key")
+res = transcriptor.assemby_ai_model("assemblyAI api key")
 
 res --> [["start", "end", "text", "speaker"], ["start", "end", "text", "speaker"]...]
 ```

library.md

@@ -70,13 +70,16 @@ transcript will also indicate the timeframe in seconds where each speaker speaks
 ### Transcription example:
 
 ```
+import os
+from speechlib import Transcriptor
+
 file = "obama_zach.wav"  # your audio file
 voices_folder = "" # voices folder containing voice samples for recognition
 language = "en"          # language code
 log_folder = "logs"      # log folder for storing transcripts
 modelSize = "tiny"     # size of model to be used [tiny, small, medium, large-v1, large-v2, large-v3]
 quantization = False   # setting this 'True' may speed up the process but lower the accuracy
-ACCESS_TOKEN = "your hf key" # get permission to access pyannote/[email protected] on huggingface
+ACCESS_TOKEN = "huggingface api key" # get permission to access pyannote/[email protected] on huggingface
 
 # quantization only works on faster-whisper
 transcriptor = Transcriptor(file, log_folder, language, modelSize, ACCESS_TOKEN, voices_folder, quantization)
@@ -94,7 +97,9 @@ res = transcriptor.custom_whisper("D:/whisper_tiny_model/tiny.pt")
 res = transcriptor.huggingface_model("Jingmiao/whisper-small-chinese_base")
 
 # use assembly ai model
-res = transcriptor.assemby_ai_model("your api key")
+res = transcriptor.assemby_ai_model("assemblyAI api key")
+
+res --> [["start", "end", "text", "speaker"], ["start", "end", "text", "speaker"]...]
 ```
 
 #### if you don't want speaker names: keep voices_folder as an empty string ""

setup.py

@@ -5,7 +5,7 @@
 
 setup(
     name="speechlib",
-    version="1.1.9",  
+    version="1.1.10",  
     description="speechlib is a library that can do speaker diarization, transcription and speaker recognition on an audio file to create transcripts with actual speaker names. This library also contain audio preprocessor functions.",
     packages=find_packages(),
     long_description=long_description,
@@ -19,7 +19,7 @@
         "Programming Language :: Python :: 3.10",
         "Operating System :: OS Independent",
     ],
-    install_requires=["transformers", "torch", "torchaudio", "pydub", "pyannote.audio", "speechbrain==0.5.16", "accelerate", "faster-whisper", "openai-whisper", "assemblyai"],
+    install_requires=["transformers>=4.36.2, <5.0.0", "torch>=2.1.2, <3.0.0", "torchaudio>=2.1.2, <3.0.0", "pydub>=0.25.1, <1.0.0", "pyannote.audio>=3.1.1, <4.0.0", "speechbrain>=0.5.16, <1.0.0", "accelerate>=0.26.1, <1.0.0", "faster-whisper>=0.10.1, <1.0.0", "openai-whisper>=20231117, <20240927", "assemblyai"],
     python_requires=">=3.8",
 )
 

setup_instruction.md

@@ -9,7 +9,7 @@ for publishing:
     pip install twine
 
 for install locally for testing:
-    pip install dist/speechlib-1.1.9-py3-none-any.whl
+    pip install dist/speechlib-1.1.10-py3-none-any.whl
 
 finally run:
     twine upload dist/*