Added App.py

app.py

@@ -0,0 +1,106 @@
+# ------------------- Type "python app.py" in TERMINAL to Run the App -------------------
+
+import torch
+import torchaudio
+import gradio as gr
+from transformers import Wav2Vec2Processor, Wav2Vec2Model
+from safetensors.torch import load_file
+import torch.nn as nn
+import torch.nn.functional as F
+
+# ------------------- Label Mapping -------------------
+
+id2label = {
+    0: "Canadian English",
+    1: "England English"
+}
+
+# ------------------- Load Processor -------------------
+
+processor = Wav2Vec2Processor.from_pretrained("creativepurus/accent-wav2vec2")
+
+# ------------------- Define Model -------------------
+
+class Wav2Vec2Classifier(nn.Module):
+    def __init__(self, num_labels):
+        super(Wav2Vec2Classifier, self).__init__()
+        self.wav2vec2 = Wav2Vec2Model.from_pretrained("facebook/wav2vec2-large-960h")
+        self.dropout = nn.Dropout(0.2)
+        self.classifier = nn.Linear(self.wav2vec2.config.hidden_size, num_labels)
+
+    def forward(self, input_values):
+        outputs = self.wav2vec2(input_values)
+        hidden_states = outputs.last_hidden_state
+        pooled_output = hidden_states.mean(dim=1)
+        logits = self.classifier(self.dropout(pooled_output))
+        return logits
+
+# ------------------- Load Weights -------------------
+
+model = Wav2Vec2Classifier(num_labels=2)
+state_dict = load_file("model.safetensors", device="cpu")  # assuming in root dir
+model.load_state_dict(state_dict)
+model.eval()
+
+# ------------------- Prediction Function -------------------
+
+def predict(audio_path):
+    # Load & preprocess audio
+    speech_array, sr = torchaudio.load(audio_path)
+    if sr != 16000:
+        resampler = torchaudio.transforms.Resample(orig_freq=sr, new_freq=16000)
+        speech_array = resampler(speech_array)
+
+    inputs = processor(
+        speech_array.squeeze().numpy(),
+        sampling_rate=16000,
+        return_tensors="pt",
+        padding="max_length",
+        truncation=True,
+        max_length=16000 * 4
+    )
+
+    with torch.no_grad():
+        logits = model(inputs.input_values)
+        probs = torch.nn.functional.softmax(logits, dim=-1)
+        pred_id = torch.argmax(probs, dim=-1).item()
+
+    return id2label[pred_id]
+
+# ------------------- Gradio UI with Dark Theme -------------------
+
+with gr.Blocks(
+    theme=gr.themes.Monochrome(primary_hue="blue", secondary_hue="purple", neutral_hue="slate"),
+    css="""
+        body { background-color: #1E1E2F !important; color: #E0E0E0 !important; }
+        .gr-button { background-color: #3B82F6 !important; color: white !important; font-weight: bold; }
+        .gr-textbox { font-size: 18px; }
+        .gr-audio label { color: white !important; }
+    """
+) as demo:
+    gr.Markdown(
+        """
+        <h1 style="text-align: center; color: #00FFFF;">🌍 Accent Classifier using Wav2Vec2</h1>
+        <p style="text-align: center; font-size: 16px;">Upload or record a 4-second <b>English voice clip</b><br>
+        This AI model detects whether your accent is <span style='color: #3B82F6; font-weight: bold;'>Canadian</span> or <span style='color: #FF4C4C; font-weight: bold;'>British</span>.</p>
+        <br>
+        """
+    )
+
+    with gr.Row():
+        with gr.Column(scale=1):
+            audio_input = gr.Audio(type="filepath", label="🎧 Upload or Record English Voice")
+            submit_btn = gr.Button("🔍 Detect Accent")
+
+        with gr.Column(scale=1):
+            label_output = gr.Text(label="🗣️ Predicted Accent")
+
+    submit_btn.click(fn=predict, inputs=audio_input, outputs=label_output)
+
+    gr.Markdown("---")
+    gr.Markdown(
+        "<p style='text-align: center;'>👨‍💻 Created by <a href='https://github.com/creativepurus' target='_blank' style='color:#66CFFF;'>Anand Purushottam</a> | <a href='https://www.linkedin.com/in/creativepurus/' target='_blank' style='color:#66CFFF;'>LinkedIn</a></p>"
+    )
+
+if __name__ == "__main__":
+    demo.launch()

requirements.txt

@@ -0,0 +1,178 @@
+absl-py==2.3.1
+accelerate==1.9.0
+aiofiles==24.1.0
+aiohappyeyeballs==2.6.1
+aiohttp==3.12.14
+aiosignal==1.4.0
+altair==5.5.0
+annotated-types==0.7.0
+anyio==4.9.0
+asttokens==3.0.0
+astunparse==1.6.3
+attrs==24.3.0
+audioread==3.0.1
+blinker==1.9.0
+Brotli==1.1.0
+cachetools==6.1.0
+certifi==2025.7.14
+cffi==1.17.1
+charset-normalizer==3.4.2
+click==8.2.1
+colorama==0.4.6
+comm==0.2.2
+contourpy==1.3.2
+cycler==0.12.1
+datasets==4.0.0
+debugpy==1.8.14
+decorator==5.2.1
+dill==0.3.8
+executing==2.2.0
+fastapi==0.116.1
+ffmpy==0.6.1
+filelock==3.18.0
+flatbuffers==25.2.10
+fonttools==4.58.5
+fpdf==1.7.2
+frozenlist==1.7.0
+fsspec==2025.3.0
+gast==0.6.0
+gitdb==4.0.12
+GitPython==3.1.44
+google-pasta==0.2.0
+gradio==5.38.2
+gradio_client==1.11.0
+groovy==0.1.2
+grpcio==1.73.1
+h11==0.16.0
+h5py==3.14.0
+hf-xet==1.1.5
+httpcore==1.0.9
+httpx==0.28.1
+huggingface-hub==0.34.1
+idna==3.10
+ipykernel==6.29.5
+ipython==9.4.0
+ipython_pygments_lexers==1.1.1
+ipywidgets==8.1.7
+jedi==0.19.2
+Jinja2==3.1.6
+joblib==1.5.1
+jsonschema==4.24.0
+jsonschema-specifications==2025.4.1
+jupyter_client==8.6.3
+jupyter_core==5.8.1
+jupyterlab_widgets==3.0.15
+keras==3.10.0
+kiwisolver==1.4.8
+lazy_loader==0.4
+libclang==18.1.1
+librosa==0.11.0
+llvmlite==0.44.0
+Markdown==3.8.2
+markdown-it-py==3.0.0
+MarkupSafe==3.0.2
+matplotlib==3.10.3
+matplotlib-inline==0.1.7
+mdurl==0.1.2
+ml_dtypes==0.5.1
+mpmath==1.3.0
+msgpack==1.1.1
+multidict==6.6.3
+multiprocess==0.70.16
+namex==0.1.0
+narwhals==1.47.0
+nest-asyncio==1.6.0
+networkx==3.5
+numba==0.61.2
+numpy==1.26.4
+opt_einsum==3.4.0
+optree==0.16.0
+orjson==3.11.1
+outcome==1.3.0.post0
+packaging==25.0
+pandas==2.3.1
+parso==0.8.4
+pillow==11.3.0
+platformdirs==4.3.8
+pooch==1.8.2
+prompt_toolkit==3.0.51
+propcache==0.3.2
+protobuf==5.29.5
+psutil==7.0.0
+pure_eval==0.2.3
+pyarrow==20.0.0
+pycparser==2.22
+pydantic==2.11.7
+pydantic_core==2.33.2
+pydeck==0.9.1
+pydub==0.25.1
+Pygments==2.19.2
+pyparsing==3.2.3
+PySocks==1.7.1
+python-dateutil==2.9.0.post0
+python-multipart==0.0.20
+pytz==2025.2
+pywin32==311
+PyYAML==6.0.2
+pyzmq==27.0.0
+referencing==0.36.2
+regex==2024.11.6
+requests==2.32.4
+rich==14.0.0
+rpds-py==0.26.0
+ruff==0.12.5
+safehttpx==0.1.6
+safetensors==0.5.3
+scikit-learn==1.7.0
+scipy==1.16.0
+seaborn==0.13.2
+selenium==4.27.1
+semantic-version==2.10.0
+setuptools==80.9.0
+shellingham==1.5.4
+six==1.17.0
+smmap==5.0.2
+sniffio==1.3.1
+sortedcontainers==2.4.0
+soundfile==0.13.1
+soxr==0.5.0.post1
+stack-data==0.6.3
+starlette==0.47.2
+streamlit==1.46.1
+sympy==1.13.1
+tenacity==9.1.2
+tensorboard==2.19.0
+tensorboard-data-server==0.7.2
+tensorflow==2.19.0
+termcolor==3.1.0
+tf_keras==2.19.0
+threadpoolctl==3.6.0
+tokenizers==0.19.1
+toml==0.10.2
+tomlkit==0.13.3
+torch==2.5.1+cu121
+torchaudio==2.5.1+cu121
+torchvision==0.20.1+cu121
+tornado==6.5.1
+tqdm==4.67.1
+traitlets==5.14.3
+transformers==4.41.2
+trio==0.27.0
+trio-websocket==0.11.1
+typer==0.16.0
+typing-inspection==0.4.1
+typing_extensions==4.14.1
+tzdata==2025.2
+urllib3==2.5.0
+uvicorn==0.35.0
+watchdog==6.0.0
+wcwidth==0.2.13
+websocket-client==1.8.0
+websockets==15.0.1
+Werkzeug==3.1.3
+wheel==0.45.1
+widgetsnbextension==4.0.14
+wrapt==1.17.2
+wsproto==1.2.0
+xxhash==3.5.0
+yarl==1.20.1