Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,40 +1,47 @@
-import altair as alt
-import numpy as np
-import pandas as pd
 import streamlit as st
-
-"""
-# Welcome to Streamlit!
-
-Edit `/streamlit_app.py` to customize this app to your heart's desire :heart:.
-If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
-forums](https://discuss.streamlit.io).
-
-In the meantime, below is an example of what you can do with just a few lines of code:
-"""
-
-num_points = st.slider("Number of points in spiral", 1, 10000, 1100)
-num_turns = st.slider("Number of turns in spiral", 1, 300, 31)
-
-indices = np.linspace(0, 1, num_points)
-theta = 2 * np.pi * num_turns * indices
-radius = indices
-
-x = radius * np.cos(theta)
-y = radius * np.sin(theta)
-
-df = pd.DataFrame({
-    "x": x,
-    "y": y,
-    "idx": indices,
-    "rand": np.random.randn(num_points),
-})
-
-st.altair_chart(alt.Chart(df, height=700, width=700)
-    .mark_point(filled=True)
-    .encode(
-        x=alt.X("x", axis=None),
-        y=alt.Y("y", axis=None),
-        color=alt.Color("idx", legend=None, scale=alt.Scale()),
-        size=alt.Size("rand", legend=None, scale=alt.Scale(range=[1, 150])),
-    ))
+import torch
+import tempfile
+import os
+import torchaudio
+from transformers import WhisperProcessor, WhisperForConditionalGeneration
+
+# Model from Hugging Face
+MODEL_NAME = "chiyo123/whisper-small-tonga"
+
+@st.cache_resource
+def load_model_and_processor():
+    processor = WhisperProcessor.from_pretrained(MODEL_NAME)
+    model = WhisperForConditionalGeneration.from_pretrained(MODEL_NAME)
+    model.eval()
+    return processor, model
+
+processor, model = load_model_and_processor()
+
+# Streamlit UI
+st.title("🗣️ Custom Whisper Transcriber")
+st.write("Upload an audio file and transcribe it using your fine-tuned Whisper model.")
+
+uploaded_file = st.file_uploader("Upload audio", type=["mp3", "wav", "flac", "m4a"])
+language = st.text_input("Target language code (e.g., loz, bemba, en)", value="loz")
+
+if uploaded_file:
+    with tempfile.NamedTemporaryFile(delete=False, suffix=".wav") as tmp:
+        tmp.write(uploaded_file.read())
+        tmp_path = tmp.name
+
+    # Load and preprocess audio
+    speech_array, sampling_rate = torchaudio.load(tmp_path)
+    speech_array = torchaudio.functional.resample(speech_array, orig_freq=sampling_rate, new_freq=16000)
+    input_values = processor(speech_array.squeeze(), return_tensors="pt", sampling_rate=16000).input_features
+
+    # Generate
+    with st.spinner("Transcribing..."):
+        forced_decoder_ids = processor.get_decoder_prompt_ids(language=language, task="transcribe")
+        predicted_ids = model.generate(input_values, forced_decoder_ids=forced_decoder_ids)
+        transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)[0]
+
+    st.subheader("📄 Transcription")
+    st.success(transcription)
+
+    # Cleanup
+    os.remove(tmp_path)