fix: revert inference and frames

chore: add extra tests

chore: add comments

chore: in-line comments

feat: add Postman collection for gRPC testing

refactor(text2video): enhance video generation with audio and filter options

chore: import numpy

fix: add video dir

fix: whisper global var

fix: path

fix: videos path

feat: add whisper audio to text

fix: inference and frames

feat: increase worker capacity

fix: reduce inference

feat: increase inference to 50

feat: increase frames and inference

fix: import

fix: reduce frames and inference

fix: use relative import

fix: path and run command

fix: proto path

fix: change workflow

fix: grpc logging

fix: pipe null check

fix: no prompt error

feat: initialize pipeline on startup

fix: zeroGpu support

fix: cuda support

chore: add logs

fix: safetensors false

fix: cache dir

fix: getcwd

fix: cache within app dir

fix: add hf_cache

fix: write permissions

feat: custom cache folder

fix: repo id

fix: gradio interface issue

fix: move files

fix: add file dir

feat: change workflow

fix: path for model

Refactor to download model at build

Fix: use /app/hf_cache for model download

refactor: change cache_dir

fix: comma error

refactor(server): move cache configuration to pipeline initialization

Fix HF model download permission error

init