added 4 files

Dockerfile

@@ -0,0 +1,28 @@
+# Use a base image
+FROM python:3.9-slim
+
+# Create and set the working directory
+WORKDIR /app
+
+# Copy the requirements file into the container at /app
+COPY requirements.txt .
+
+# Install Python packages using pip
+RUN pip install --no-cache-dir --upgrade pip && \
+    pip install --no-cache-dir --upgrade setuptools && \
+    pip install --no-cache-dir wheel && \
+    pip install --no-cache-dir -r requirements.txt
+
+# Copy the current directory contents into the container at /app
+COPY . .
+
+# Set permissions for the application directory
+RUN chown -R root:root /app
+RUN chmod -R 755 /app
+
+# Expose the port the app runs on
+EXPOSE 7860
+
+# Command to run the application
+CMD ["python3", "app.py"]
+

app.py

@@ -0,0 +1,39 @@
+import gradio as gr
+from vosk import Model, KaldiRecognizer
+import wave
+import json
+
+# Set up the Vosk model
+model = Model("vosk-model-small-uz-0.22")
+
+def recognize_from_file(audio_file):
+    wf = wave.open(audio_file, "rb")
+    if wf.getnchannels() != 1 or wf.getsampwidth() != 2 or wf.getcomptype() != "NONE":
+        return "Audio file must be WAV format mono PCM."
+
+    recognizer = KaldiRecognizer(model, wf.getframerate())
+    result_text = ""
+
+    while True:
+        data = wf.readframes(4000)
+        if len(data) == 0:
+            break
+        if recognizer.AcceptWaveform(data):
+            result = json.loads(recognizer.Result())
+            result_text += result.get('text', '') + " "
+
+    final_result = json.loads(recognizer.FinalResult())
+    result_text += final_result.get('text', '')
+
+    return result_text
+
+
+iface = gr.Interface(
+    fn=recognize_from_file,
+    inputs=gr.Audio(type="filepath"),
+    outputs="text",
+    title="Speech Recognition from Audio File",
+    description="Upload a WAV file for recognition."
+)
+
+iface.launch()

requirements.txt

@@ -0,0 +1,3 @@
+vosk
+PyAudio
+gradio