Minor cleanup and added TODO comments

Dockerfile.gpu

@@ -34,4 +34,4 @@ COPY . .
 RUN poetry install
 RUN $POETRY_VENV/bin/pip install torch==1.13.0+cu117 -f https://download.pytorch.org/whl/torch
 
-CMD PYTHONUNBUFFERED=TRUE gunicorn --bind 0.0.0.0:9000 --workers 1 --timeout 0 app.webservice:app -k uvicorn.workers.UvicornWorker
+CMD gunicorn --bind 0.0.0.0:9000 --workers 1 --timeout 0 app.webservice:app -k uvicorn.workers.UvicornWorker

app/faster_whisper/utils.py

@@ -1,20 +1,6 @@
 import json
 import os
-import sys
-import zlib
-from typing import Callable, TextIO
-
-system_encoding = sys.getdefaultencoding()
-
-if system_encoding != "utf-8":
-    def make_safe(string):
-        # replaces any character not representable using the system default encoding with an '?',
-        # avoiding UnicodeEncodeError (https://github.com/openai/whisper/discussions/729).
-        return string.encode(system_encoding, errors="replace").decode(system_encoding)
-else:
-    def make_safe(string):
-        # utf-8 can encode any Unicode code point, so no need to do the round-trip encoding
-        return string
+from typing import TextIO
 
 
 def format_timestamp(seconds: float, always_include_hours: bool = False, decimal_marker: str = '.'):

model_conversion.sh

@@ -1,3 +1,4 @@
 #!/bin/bash
 
+# TODO: Add step to build setup based on ENV variable
 ct2-transformers-converter --model openai/whisper-large-v2 --output_dir /root/.cache/faster_whisper --quantization float16