Add dotenv, fixed requirements.txt

.env.sample

@@ -0,0 +1,2 @@
+MODEL="m3hrdadfi/wav2vec2-large-xlsr-persian"
+LOG_LEVEL="INFO"

main.py

@@ -1,20 +1,27 @@
 import logging
+import os
+import warnings
 
 import librosa
+import transformers
 import torch
+from dotenv import load_dotenv
 from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
 
-# MODEL = "m3hrdadfi/wav2vec2-large-xlsr-persian"
+
-MODEL = "/home/reza/data/huggingface-models/04.wav2vec2-large-xlsr-persian"
+warnings.filterwarnings("ignore")
+transformers.logging.set_verbosity_error()
+load_dotenv()
+MODEL = os.getenv("MODEL", "m3hrdadfi/wav2vec2-large-xlsr-persian")
+LOG_LEVEL = os.getenv("LOG_LEVEL", "DEBUG")
 
 
-def initLogger(name=__name__, level=logging.DEBUG):
+def initLogger():
-    if name[:2] == '__' and name[-2:] == '__':
+    logger = logging.getLogger("speech2text-fa")
-        name = name[2:-2]
+    level = getattr(logging, LOG_LEVEL.upper())
-    logger = logging.getLogger(name)
     
-    fmt = '%(asctime)s | %(levelname)-8s | %(name)s | %(message)s'
+    fmt = "%(asctime)s | %(levelname)-8s | %(message)s"
-    datefmt = '%Y-%m-%d %H:%M:%S'
+    datefmt = "%Y-%m-%d %H:%M:%S"
     ch = logging.StreamHandler()
     ch.setLevel(logging.DEBUG)
     formatter = logging.Formatter(fmt, datefmt)
@@ -49,7 +56,7 @@ def mp3_to_text(mp3_file_path):
 
 
 if __name__ == "__main__":
-    logger = initLogger('speech2text_fa', level=logging.INFO)
+    logger = initLogger()
     text = mp3_to_text("samples/sample1.wav")
     print()
     print(text)

requirements.txt

@@ -1,6 +1,6 @@
-torch==2.1.1+cpu
+https://download.pytorch.org/whl/cpu/torch-2.1.1%2Bcpu-cp311-cp311-linux_x86_64.whl#sha256=d83b13cb17544f9851cc31fed197865eae0c0f5d32df9d8d6d8535df7d2e5109
-torchaudio==2.1.1+cpu
+https://download.pytorch.org/whl/cpu/torchaudio-2.1.1%2Bcpu-cp311-cp311-linux_x86_64.whl#sha256=e0eb276958fcbd7c88f5daf761823e36ce5e41332d40f9e01fb49d80d7cc1bb1
-transformers==4.35.2
 librosa==0.10.1
-
+python-dotenv==1.0.0
---find-links https://download.pytorch.org/whl/cpu
+tokenizers>=0.10.1,<0.11
+transformers>=4.16.2,<4.17.0