model loading check

app.py

@@ -1,121 +1,23 @@
-"""
-Streamlit application for real-time gender detection from audio input.
-Uses wav2vec2 model to analyze voice and predict speaker gender.
-"""
 import streamlit as st
-import pyaudio
 import numpy as np
 import torch
 from transformers import AutoFeatureExtractor, AutoModelForAudioClassification
-import logging
-
-# Configure logging
-logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
-
-# Define audio stream parameters
-FORMAT = pyaudio.paInt16  # 16-bit resolution
-CHANNELS = 1              # Mono audio
-RATE = 16000              # 16kHz sampling rate
-CHUNK = 1024              # Number of frames per buffer
+from streamlit_webrtc import webrtc_streamer, AudioProcessorBase, WebRtcMode
+import av
 
+# Load Model and Feature Extractor
 @st.cache_resource
 def load_model():
     """
     Load the wav2vec2 model and feature extractor for gender recognition.
-
-    Returns:
-        tuple: A tuple containing the feature extractor and the model.
     """
     model_path = "alefiury/wav2vec2-large-xlsr-53-gender-recognition-librispeech"
-    # model_path = "./local-model"
     feature_extractor = AutoFeatureExtractor.from_pretrained(model_path)
     model = AutoModelForAudioClassification.from_pretrained(model_path)
     model.eval()
-    logging.info("Model loaded successfully.")
     return feature_extractor, model
 
-st.title("Gender Detection")
-
-# Initialize session state
-if 'listening' not in st.session_state:
-    st.session_state['listening'] = False
-if 'prediction' not in st.session_state:
-    st.session_state['prediction'] = ""
-
-# Function to stop listening
-def stop_listening():
-    """Stop the audio stream and update session state to stop listening."""
-    if 'stream' in st.session_state:
-        logging.info("Stopping stream")
-        st.session_state['stream'].stop_stream()
-        st.session_state['stream'].close()
-    if 'audio' in st.session_state:
-        logging.info("Stopping audio")
-        st.session_state['audio'].terminate()
-    st.session_state['listening'] = False
-    st.session_state['prediction'] = "Stopped listening, click 'Start Listening' to start again."
-    st.rerun()
-
-def start_listening():
-    """Start the audio stream and continuously process audio for gender detection."""
-    placeholder = st.empty()
-    try:
-        placeholder.write("Loading model...")
-        feature_extractor, model = load_model()
-        audio = pyaudio.PyAudio()
-        stream = audio.open(format=FORMAT,
-                            channels=CHANNELS,
-                            rate=RATE,
-                            input=True,
-                            frames_per_buffer=CHUNK)
-
-        st.session_state['stream'] = stream
-        st.session_state['audio'] = audio
-        st.session_state['listening'] = True
-        st.session_state['prediction'] = "Listening........................"
-        placeholder.write("Listening for audio...")
-
-        while st.session_state['listening']:
-            audio_data = np.array([], dtype=np.float32)
-
-            for _ in range(int(RATE / CHUNK * 1.5)):
-                # Read audio chunk from the stream
-                data = stream.read(CHUNK, exception_on_overflow=False)
-                
-                # Convert byte data to numpy array and normalize
-                chunk_data = np.frombuffer(data, dtype=np.int16).astype(np.float32) / 32768.0
-                audio_data = np.concatenate((audio_data, chunk_data))
-
-            # Check if there is significant sound
-            if np.max(np.abs(audio_data)) > 0.05:  # Threshold for detecting sound
-                # Process the audio data
-                inputs = feature_extractor(audio_data, sampling_rate=RATE, return_tensors="pt", padding=True)
-                # Perform inference
-                with torch.no_grad():
-                    logits = model(**inputs).logits
-                    predicted_ids = torch.argmax(logits, dim=-1)
-
-                    # Map predicted IDs to labels
-                    predicted_label = model.config.id2label[predicted_ids.item()]
-
-                    if predicted_label != st.session_state['prediction']:
-                        st.session_state['prediction'] = predicted_label
-                        # st.write(f"Detected Gender: {predicted_label}")
-                        placeholder.write(f"Detected Gender: {predicted_label}")
-            else:
-                st.session_state['prediction'] = "---- No significant sound detected, skipping prediction. ----"
-                placeholder.empty()
-        placeholder.empty()
-    except Exception as e:
-        logging.error(f"An error occurred: {e}")
-        st.error(f"An error occurred: {e}")
-        stop_listening()
-
-# Buttons to start and stop listening
-col1, col2 = st.columns(2)
-with col1:
-    if st.button("Start Listening"):
-        start_listening()
-with col2:
-    if st.button("Stop Listening"):
-        stop_listening()
+placeholder = st.empty()
+placeholder.text("Loading model...")
+feature_extractor, model = load_model()
+placeholder.text("Model loaded!")    

requirements.txt

@@ -1,66 +1,399 @@
+aiobotocore==2.5.0
+aiofiles==22.1.0
+aiohttp==3.8.5
 aioice==0.9.0
+aioitertools==0.7.1
 aiortc==1.10.1
+aiosignal==1.2.0
+aiosqlite==0.18.0
+alabaster==0.7.12
 altair==5.5.0
-attrs==25.1.0
+anaconda-anon-usage==0.4.2
+anaconda-catalogs==0.2.0
+anaconda-client==1.12.1
+anaconda-cloud-auth==0.1.3
+anaconda-navigator==2.5.0
+anaconda-project==0.11.1
+annotated-types==0.7.0
+anyio==3.5.0
+appdirs==1.4.4
+applaunchservices==0.3.0
+appnope==0.1.2
+appscript==1.1.2
+argon2-cffi==21.3.0
+argon2-cffi-bindings==21.2.0
+arrow==1.2.3
+astroid==2.14.2
+astropy==5.1
+asttokens==2.0.5
+async-timeout==4.0.2
+atomicwrites==1.4.0
+attrs==22.1.0
+Automat==20.2.0
+autopep8==1.6.0
 av==13.1.0
+Babel==2.11.0
+backcall==0.2.0
+backports.functools-lru-cache==1.6.4
+backports.tempfile==1.0
+backports.weakref==1.0.post1
+bcrypt==3.2.0
+beautifulsoup4==4.12.2
+binaryornot==0.4.4
+black==0.0
+bleach==4.1.0
 blinker==1.9.0
+bokeh==3.2.1
+boltons==23.0.0
+botocore==1.29.76
+Bottleneck==1.3.5
+brotlipy==0.7.0
 cachetools==5.5.1
-certifi==2025.1.31
-cffi==1.17.1
-charset-normalizer==3.4.1
-click==8.1.8
+certifi==2023.7.22
+cffi==1.15.1
+chardet==4.0.0
+charset-normalizer==2.0.4
+click==8.0.4
+cloudpickle==2.2.1
+clyent==1.2.2
+colorama==0.4.6
+colorcet==3.0.1
+comm==0.1.2
+conda==23.7.4
+conda-build==3.26.1
+conda-content-trust==0.2.0
+conda_index==0.3.0
+conda-libmamba-solver==23.7.0
+conda-pack==0.6.0
+conda-package-handling==2.2.0
+conda_package_streaming==0.9.0
+conda-repo-cli==1.0.75
+conda-token==0.4.0
+conda-verify==3.4.2
+constantly==15.1.0
+contourpy==1.0.5
+cookiecutter==1.7.3
 cryptography==44.0.1
+cssselect==1.1.0
+cycler==0.11.0
+cytoolz==0.12.0
+dask==2023.6.0
+datasets==2.12.0
+datashader==0.15.2
+datashape==0.5.4
+debugpy==1.6.7
+decorator==5.1.1
+defusedxml==0.7.1
+diff-match-patch==20200713
+dill==0.3.6
+distributed==2023.6.0
+distro==1.9.0
 dnspython==2.7.0
-filelock==3.17.0
-fsspec==2025.2.0
+docstring-to-markdown==0.11
+docutils==0.18.1
+entrypoints==0.4
+et-xmlfile==1.1.0
+executing==0.8.3
+fastjsonschema==2.16.2
+filelock==3.9.0
+flake8==6.0.0
+Flask==2.2.2
+fonttools==4.25.0
+frozenlist==1.3.3
+fsspec==2023.4.0
+future==0.18.3
+gensim==4.3.0
 gitdb==4.0.12
 GitPython==3.1.44
+glob2==0.7
+gmpy2==2.1.2
 google-crc32c==1.6.0
-huggingface-hub==0.28.1
-idna==3.10
+greenlet==2.0.1
+h11==0.14.0
+h5py==3.9.0
+HeapDict==1.0.1
+holoviews==1.17.1
+httpcore==1.0.7
+httpx==0.28.0
+huggingface-hub==0.15.1
+hvplot==0.8.4
+hyperlink==21.0.0
+idna==3.4
 ifaddr==0.2.0
-Jinja2==3.1.5
-jsonschema==4.23.0
-jsonschema-specifications==2024.10.1
-markdown-it-py==3.0.0
-MarkupSafe==3.0.2
-mdurl==0.1.2
+imagecodecs==2023.1.23
+imageio==2.31.1
+imagesize==1.4.1
+imbalanced-learn==0.10.1
+importlib-metadata==6.0.0
+incremental==21.3.0
+inflection==0.5.1
+iniconfig==1.1.1
+intake==0.6.8
+intervaltree==3.1.0
+ipykernel==6.25.0
+ipython==8.15.0
+ipython-genutils==0.2.0
+ipywidgets==8.0.4
+isort==5.9.3
+itemadapter==0.3.0
+itemloaders==1.0.4
+itsdangerous==2.0.1
+jaraco.classes==3.2.1
+jedi==0.18.1
+jellyfish==1.0.1
+Jinja2==3.1.2
+jinja2-time==0.2.0
+jiter==0.8.0
+jmespath==0.10.0
+joblib==1.2.0
+json5==0.9.6
+jsonpatch==1.33
+jsonpointer==2.1
+jsonschema==4.17.3
+jupyter==1.0.0
+jupyter_client==7.4.9
+jupyter-console==6.6.3
+jupyter_core==5.3.0
+jupyter-events==0.6.3
+jupyter-server==1.23.4
+jupyter_server_fileid==0.9.0
+jupyter_server_ydoc==0.8.0
+jupyter-ydoc==0.2.4
+jupyterlab==3.6.3
+jupyterlab-pygments==0.1.2
+jupyterlab_server==2.22.0
+jupyterlab-widgets==3.0.5
+kaleido==0.2.1
+keyring==23.13.1
+kiwisolver==1.4.4
+langchain==0.3.9
+langchain-core==0.3.21
+langchain-text-splitters==0.3.2
+langsmith==0.1.147
+lazy_loader==0.2
+lazy-object-proxy==1.6.0
+libarchive-c==2.9
+libmambapy==1.5.1
+linkify-it-py==2.0.0
+llvmlite==0.40.0
+lmdb==1.4.1
+locket==1.0.0
+lxml==4.9.3
+lz4==4.3.2
+Markdown==3.4.1
+markdown-it-py==2.2.0
+MarkupSafe==2.1.1
+matplotlib==3.7.2
+matplotlib-inline==0.1.6
+mccabe==0.7.0
+mdit-py-plugins==0.3.0
+mdurl==0.1.0
+mistune==0.8.4
+more-itertools==8.12.0
 mpmath==1.3.0
+msgpack==1.0.3
+multidict==6.0.2
+multipledispatch==0.6.0
+multiprocess==0.70.14
+munkres==1.1.4
+mypy-extensions==1.0.0
 narwhals==1.26.0
-networkx==3.4.2
-numpy==2.2.3
+navigator-updater==0.4.0
+nbclassic==0.5.5
+nbclient==0.5.13
+nbconvert==6.5.4
+nbformat==5.9.2
+nest-asyncio==1.5.6
+networkx==3.1
+nltk==3.8.1
+notebook==6.5.4
+notebook_shim==0.2.2
+numba==0.57.1
+numexpr==2.8.4
+numpy==1.24.3
+numpydoc==1.5.0
+openai==1.55.3
+openpyxl==3.0.10
+orjson==3.10.12
 packaging==24.2
-pandas==2.2.3
-pillow==11.1.0
+pandas==2.0.3
+pandocfilters==1.5.0
+panel==1.2.3
+param==1.13.0
+parsel==1.6.0
+parso==0.8.3
+partd==1.4.0
+pathlib==1.0.1
+pathspec==0.10.3
+patsy==0.5.3
+pep8==1.7.1
+pexpect==4.8.0
+pickleshare==0.7.5
+Pillow==9.4.0
+pip==23.2.1
+pkce==1.0.3
+pkginfo==1.9.6
+platformdirs==3.10.0
+plotly==5.9.0
+pluggy==1.0.0
+ply==3.11
+poyo==0.5.0
+prometheus-client==0.14.1
+prompt-toolkit==3.0.36
+Protego==0.1.16
 protobuf==5.29.3
-pyarrow==19.0.0
-pycparser==2.22
+psutil==5.9.0
+psycopg2==2.9.9
+ptyprocess==0.7.0
+pure-eval==0.2.2
+py-cpuinfo==8.0.0
+pyarrow==11.0.0
+pyasn1==0.4.8
+pyasn1-modules==0.2.8
+PyAudio==0.2.14
+pycodestyle==2.10.0
+pycosat==0.6.4
+pycparser==2.21
+pyct==0.5.0
+pycurl==7.45.2
+pydantic==2.10.2
+pydantic_core==2.27.1
 pydeck==0.9.1
+PyDispatcher==2.0.5
+pydocstyle==6.3.0
 pyee==12.1.1
-Pygments==2.19.1
+pyerfa==2.0.0
+pyflakes==3.0.1
+Pygments==2.15.1
+PyJWT==2.4.0
 pylibsrtp==0.11.0
+pylint==2.16.2
+pylint-venv==2.3.0
+pyls-spyder==0.4.0
+pyobjc-core==9.0
+pyobjc-framework-Cocoa==9.0
+pyobjc-framework-CoreServices==9.0
+pyobjc-framework-FSEvents==9.0
+pyodbc==4.0.34
 pyOpenSSL==25.0.0
-python-dateutil==2.9.0.post0
-pytz==2025.1
-PyYAML==6.0.2
-referencing==0.36.2
-regex==2024.11.6
-requests==2.32.3
+pyparsing==3.0.9
+PyQt5-sip==12.11.0
+pyrsistent==0.18.0
+PySocks==1.7.1
+pytest==7.4.0
+python-dateutil==2.8.2
+python-dotenv==0.21.0
+python-json-logger==2.0.7
+python-lsp-black==1.2.1
+python-lsp-jsonrpc==1.0.0
+python-lsp-server==1.7.2
+python-slugify==5.0.2
+python-snappy==0.6.1
+pytoolconfig==1.2.5
+pytz==2023.3.post1
+pyviz-comms==2.3.0
+PyWavelets==1.4.1
+PyYAML==6.0
+pyzmq==23.2.0
+QDarkStyle==3.0.2
+qstylizer==0.2.2
+QtAwesome==1.2.2
+qtconsole==5.4.2
+QtPy==2.2.0
+queuelib==1.5.0
+regex==2022.7.9
+requests==2.31.0
+requests-file==1.5.1
+requests-toolbelt==1.0.0
+responses==0.13.3
+rfc3339-validator==0.1.4
+rfc3986-validator==0.1.1
 rich==13.9.4
-rpds-py==0.22.3
-safetensors==0.5.2
-six==1.17.0
+rope==1.7.0
+Rtree==1.0.1
+ruamel.yaml==0.17.21
+ruamel-yaml-conda==0.17.21
+s3fs==2023.4.0
+safetensors==0.3.2
+scikit-image==0.20.0
+scikit-learn==1.3.0
+scipy==1.11.1
+Scrapy==2.8.0
+seaborn==0.12.2
+Send2Trash==1.8.0
+service-identity==18.1.0
+setuptools==68.0.0
+sip==6.6.2
+six==1.16.0
+smart-open==5.2.1
 smmap==5.0.2
+sniffio==1.2.0
+snowballstemmer==2.2.0
+sortedcontainers==2.4.0
+soupsieve==2.4
+Sphinx==5.0.2
+sphinxcontrib-applehelp==1.0.2
+sphinxcontrib-devhelp==1.0.2
+sphinxcontrib-htmlhelp==2.0.0
+sphinxcontrib-jsmath==1.0.1
+sphinxcontrib-qthelp==1.0.3
+sphinxcontrib-serializinghtml==1.1.5
+spyder==5.4.3
+spyder-kernels==2.4.4
+SQLAlchemy==1.4.39
+stack-data==0.2.0
+statsmodels==0.14.0
 streamlit==1.42.0
 streamlit-webrtc==0.47.9
 sympy==1.13.1
-tenacity==9.0.0
-tokenizers==0.21.0
+tables==3.8.0
+tabulate==0.8.10
+tblib==1.7.0
+tenacity==8.2.2
+terminado==0.17.1
+text-unidecode==1.3
+textdistance==4.2.1
+threadpoolctl==2.2.0
+three-merge==0.1.1
+tifffile==2023.4.12
+tinycss2==1.2.1
+tldextract==3.2.0
+tokenizers==0.13.2
 toml==0.10.2
+tomlkit==0.11.1
+toolz==0.12.0
 torch==2.6.0
-tornado==6.4.2
-tqdm==4.67.1
-transformers==4.48.3
+tornado==6.3.2
+tqdm==4.65.0
+traitlets==5.7.1
+transformers==4.32.1
+Twisted==22.10.0
 typing_extensions==4.12.2
-tzdata==2025.1
-urllib3==2.3.0
+tzdata==2023.3
+uc-micro-py==1.0.1
+ujson==5.4.0
+Unidecode==1.2.0
+urllib3==1.26.16
+w3lib==1.21.0
+watchdog==2.1.6
+wcwidth==0.2.5
+webencodings==0.5.1
+websocket-client==0.58.0
+Werkzeug==2.2.3
+whatthepatch==1.0.2
+wheel==0.38.4
+widgetsnbextension==4.0.5
+wrapt==1.14.1
+wurlitzer==3.0.2
+xarray==2023.6.0
+xlwings==0.29.1
+xxhash==2.0.2
+xyzservices==2022.9.0
+y-py==0.5.9
+yapf==0.31.0
+yarl==1.8.1
+ypy-websocket==0.8.2
+zict==2.2.0
+zipp==3.11.0
+zope.interface==5.4.0
+zstandard==0.19.0