Setup Overview #
My setup consists of an NVIDIA GTX 1060 GPU with CachyOS Linux.
Python Prerequisites #
Create Python Venv #
CachyOS uses fish as the default shell, adapt activate.fish if necessary.
# Create virtual environment
python3 -m venv .venv-hf-project-2
# Active environment
source .venv-hf-project-2/bin/activate.fish
# Upgrade pip
pip install --upgrade pip
# (Deactivate venv)
deactivate
Pip Requirements #
Create Pinned Version List #
Find CUDA version: https://download.pytorch.org/whl/
# List available versions
pip index versions torchaudio \
--index-url https://download.pytorch.org/whl/cu118
# Shell output:
torch (2.7.1+cu118)
Available versions: 2.7.1+cu118, 2.7.0+cu118, 2.6.0+cu118, 2.5.1+cu118, 2.5.0+cu118
Create a file with the intented packages:
- requirements.in
--index-url https://download.pytorch.org/whl/cu118
--extra-index-url https://pypi.org/simple
torch==2.7.1+cu118
torchaudio==2.7.1+cu118
python-dotenv
pillow
streamlit
scipy
transformers
accelerate
datasets
huggingface_hub
# Install pip tools
pip install pip-tools
# Create a txt file with the exact pinned package and dependencies versions
pip-compile -o requirements.txt requirements.in
The pinned down requirements and their dependencies look like this:
- requirements.txt
#
# This file is autogenerated by pip-compile with Python 3.13
# by the following command:
#
# pip-compile --output-file=requirements.txt requirements.in
#
--index-url https://download.pytorch.org/whl/cu118
--extra-index-url https://pypi.org/simple
accelerate==1.12.0
# via -r requirements.in
aiohappyeyeballs==2.6.1
# via aiohttp
aiohttp==3.13.2
# via fsspec
aiosignal==1.4.0
# via aiohttp
altair==6.0.0
# via streamlit
anyio==4.12.0
# via httpx
attrs==25.4.0
# via
# aiohttp
# jsonschema
# referencing
blinker==1.9.0
# via streamlit
cachetools==6.2.2
# via streamlit
certifi==2025.11.12
# via
# httpcore
# httpx
# requests
charset-normalizer==3.4.4
# via requests
click==8.3.1
# via streamlit
datasets==4.4.1
# via -r requirements.in
dill==0.4.0
# via
# datasets
# multiprocess
filelock==3.20.0
# via
# datasets
# huggingface-hub
# torch
# transformers
frozenlist==1.8.0
# via
# aiohttp
# aiosignal
fsspec[http]==2025.10.0
# via
# datasets
# huggingface-hub
# torch
gitdb==4.0.12
# via gitpython
gitpython==3.1.45
# via streamlit
h11==0.16.0
# via httpcore
hf-xet==1.2.0
# via huggingface-hub
httpcore==1.0.9
# via httpx
httpx==0.28.1
# via datasets
huggingface-hub==0.36.0
# via
# -r requirements.in
# accelerate
# datasets
# tokenizers
# transformers
idna==3.11
# via
# anyio
# httpx
# requests
# yarl
jinja2==3.1.6
# via
# altair
# pydeck
# torch
jsonschema==4.25.1
# via altair
jsonschema-specifications==2025.9.1
# via jsonschema
markupsafe==3.0.3
# via jinja2
mpmath==1.3.0
# via sympy
multidict==6.7.0
# via
# aiohttp
# yarl
multiprocess==0.70.18
# via datasets
narwhals==2.13.0
# via altair
networkx==3.6.1
# via torch
numpy==2.3.5
# via
# accelerate
# datasets
# pandas
# pydeck
# scipy
# streamlit
# transformers
nvidia-cublas-cu11==11.11.3.6
# via
# nvidia-cudnn-cu11
# nvidia-cusolver-cu11
# torch
nvidia-cuda-cupti-cu11==11.8.87
# via torch
nvidia-cuda-nvrtc-cu11==11.8.89
# via torch
nvidia-cuda-runtime-cu11==11.8.89
# via torch
nvidia-cudnn-cu11==9.1.0.70
# via torch
nvidia-cufft-cu11==10.9.0.58
# via torch
nvidia-curand-cu11==10.3.0.86
# via torch
nvidia-cusolver-cu11==11.4.1.48
# via torch
nvidia-cusparse-cu11==11.7.5.86
# via torch
nvidia-nccl-cu11==2.21.5
# via torch
nvidia-nvtx-cu11==11.8.86
# via torch
packaging==25.0
# via
# accelerate
# altair
# datasets
# huggingface-hub
# streamlit
# transformers
pandas==2.3.3
# via
# datasets
# streamlit
pillow==12.0.0
# via
# -r requirements.in
# streamlit
propcache==0.4.1
# via
# aiohttp
# yarl
protobuf==6.33.2
# via streamlit
psutil==7.1.3
# via accelerate
pyarrow==22.0.0
# via
# datasets
# streamlit
pydeck==0.9.1
# via streamlit
python-dateutil==2.9.0.post0
# via pandas
python-dotenv==1.2.1
# via -r requirements.in
pytz==2025.2
# via pandas
pyyaml==6.0.3
# via
# accelerate
# datasets
# huggingface-hub
# transformers
referencing==0.37.0
# via
# jsonschema
# jsonschema-specifications
regex==2025.11.3
# via transformers
requests==2.32.5
# via
# datasets
# huggingface-hub
# streamlit
# transformers
rpds-py==0.30.0
# via
# jsonschema
# referencing
safetensors==0.7.0
# via
# accelerate
# transformers
scipy==1.16.3
# via -r requirements.in
six==1.17.0
# via python-dateutil
smmap==5.0.2
# via gitdb
streamlit==1.52.1
# via -r requirements.in
sympy==1.14.0
# via torch
tenacity==9.1.2
# via streamlit
tokenizers==0.22.1
# via transformers
toml==0.10.2
# via streamlit
torch==2.7.1+cu118
# via
# -r requirements.in
# accelerate
# torchaudio
torchaudio==2.7.1+cu118
# via -r requirements.in
tornado==6.5.3
# via streamlit
tqdm==4.67.1
# via
# datasets
# huggingface-hub
# transformers
transformers==4.57.3
# via -r requirements.in
triton==3.3.1
# via torch
typing-extensions==4.15.0
# via
# altair
# huggingface-hub
# streamlit
# torch
tzdata==2025.2
# via pandas
urllib3==2.6.2
# via requests
watchdog==6.0.0
# via streamlit
xxhash==3.6.0
# via datasets
yarl==1.22.0
# via aiohttp
# The following packages are considered to be unsafe in a requirements file:
# setuptools
Insall Requirements #
# Install pinned requirements and dependencies
pip install -r requirements.txt
Python App #
Hugging Face Model #
Model Link: https://huggingface.co/Salesforce/blip-image-captioning-base
File and Folder Structure #
The file and folder structure of the project looks like this:
hf-project-2
├── app.py
├── caption.wav # Created / overwritten by the text to audio model
├── .env
├── requirements.in
└── requirements.txt
.env File & HF API Token #
Create Hugging Face API token:
-
Go to: “Settings” > “Access Tokens” > “Create new token”
-
Select “Read”
-
Click “Create token”
Add the token to the .env file:
- .env
# Hugging Face read token
HUGGINGFACEHUB_API_TOKEN=mysecuretoken
Python app.py #
from dotenv import find_dotenv, load_dotenv
from transformers import pipeline
from PIL import Image
from scipy.io.wavfile import write as write_wav
import streamlit as st
import numpy as np
import os
# Load variables from .env file
load_dotenv(find_dotenv())
# Function load model: image2text
@st.cache_resource # Cache the model
def load_model_img_to_text():
return pipeline(
"image-to-text",
model="Salesforce/blip-image-captioning-base",
device="cuda:0"
) # Omit device to let it auto-detect
# Function load model: text2speech
@st.cache_resource
def load_model_text_to_speech():
return pipeline(
"text-to-speech",
model="suno/bark-small",
device="cuda:0",
) # Omit device to let it auto-detect
# Call function for image2text model > becomes pipeline object
model_img_to_text = load_model_img_to_text()
# Call function for text_to_speech > becomes pipeline object
model_text_to_speech = load_model_text_to_speech()
# Function: text2speech settings
def text_to_speech(text: str, output_file: str = "caption.wav") -> None:
speech = model_text_to_speech(text)
# Bark pipeline returns a float waveform and sampling rate
audio_array = speech["audio"]
sample_rate = speech["sampling_rate"]
# Ensure numpy array
audio_array = np.array(audio_array).astype(np.float32).flatten()
# Convert to 16-bit PCM for WAV
audio_int16 = (audio_array * 32767).astype(np.int16)
write_wav(output_file, sample_rate, audio_int16)
print(f"Audio saved as: {output_file}")
# Streamlit UI
st.title("Image to Text to Audio Demo")
st.write("Upload an image and output the description with audio")
uploaded_file = st.file_uploader(
"Upload image:",
type=["jpg", "jpeg", "png"]
)
if uploaded_file is not None:
# Open and show the image
image = Image.open(uploaded_file).convert("RGB")
st.image(image, caption="Uploaded image", width=700)
if st.button("Generate caption & audio"):
with st.spinner("Running model..."):
# Image -> Text
img_to_text = model_img_to_text(image)
caption = img_to_text[0]["generated_text"]
# Text -> Audio (save to WAV)
audio_path = "caption.wav"
text_to_speech(caption, audio_path)
# Read WAV for Streamlit
with open(audio_path, "rb") as f:
audio_bytes = f.read()
st.success("Caption:")
st.write(caption)
st.audio(audio_bytes, format="audio/wav")
Run App #
# Run app
streamlit run app.py
# Shell output:
You can now view your Streamlit app in your browser.
Local URL: http://localhost:8501
Network URL: http://192.168.70.21:8501
# Open app in browser
http://192.168.70.21:8501
The Python Streamlit UI looks like this:
