Update app.py

app.py

@@ -89,46 +89,46 @@
 
 # demo.launch()
 
-import gradio as gr
+# import gradio as gr
 
 
-def calculator(num1, operation, num2):
-    if operation == "add":
-        return num1 + num2
-    elif operation == "subtract":
-        return num1 - num2
-    elif operation == "multiply":
-        return num1 * num2
-    elif operation == "divide":
-        return num1 / num2
+# def calculator(num1, operation, num2):
+#     if operation == "add":
+#         return num1 + num2
+#     elif operation == "subtract":
+#         return num1 - num2
+#     elif operation == "multiply":
+#         return num1 * num2
+#     elif operation == "divide":
+#         return num1 / num2
 
 
-iface = gr.Interface(
-    calculator,
-    ["number", gr.Radio(["add", "subtract", "multiply", "divide"]), "number"],
-    "number",
-    allow_flagging="manual",
-    flagging_options=["correct", "wrong"]
-)
+# iface = gr.Interface(
+#     calculator,
+#     ["number", gr.Radio(["add", "subtract", "multiply", "divide"]), "number"],
+#     "number",
+#     allow_flagging="manual",
+#     flagging_options=["correct", "wrong"]
+# )
 
-iface.launch()
+# iface.launch()
 
-import os
+# import os
 
-HF_TOKEN = os.getenv('HF_TOKEN')
-hf_writer = gr.HuggingFaceDatasetSaver(HF_TOKEN, "crowdsourced")
-
-iface = gr.Interface(
-    calculator,
-    ["number", gr.Radio(["add", "subtract", "multiply", "divide"]), "number"],
-    "number",
-    description="Check out the crowd-sourced dataset at: [https://huggingface.co/Sajjo/crowdsourced](https://huggingface.co/Sajjo/crowdsourced)",
-    allow_flagging="manual",
-    flagging_options=["wrong sign", "off by one", "other"],
-    flagging_callback=hf_writer
-)
+# HF_TOKEN = os.getenv('HF_TOKEN')
+# hf_writer = gr.HuggingFaceDatasetSaver(HF_TOKEN, "crowdsourced")
 
-iface.launch()
+# iface = gr.Interface(
+#     calculator,
+#     ["number", gr.Radio(["add", "subtract", "multiply", "divide"]), "number"],
+#     "number",
+#     description="Check out the crowd-sourced dataset at: [https://huggingface.co/Sajjo/crowdsourced](https://huggingface.co/Sajjo/crowdsourced)",
+#     allow_flagging="manual",
+#     flagging_options=["wrong sign", "off by one", "other"],
+#     flagging_callback=hf_writer
+# )
+
+# iface.launch()
 
 # import numpy as np
 # import gradio as gr
@@ -162,3 +162,98 @@ iface.launch()
 #     btn.click(lambda *args: callback.flag(args), [img_input, strength, img_output], None, preprocess=False)
 
 # demo.launch()
+
+import gradio as gr
+import os
+import wave
+import tempfile
+import numpy as np
+
+# Global variables to store file and line index
+file_index = 0
+line_index = 0
+lines = []
+
+# Hugging Face token and dataset saver
+HF_TOKEN = os.getenv('HF_TOKEN')
+hf_writer = gr.HuggingFaceDatasetSaver(HF_TOKEN, "crowdsourced-calculator-demo")
+
+# Function to read lines from a file
+def read_lines_from_file(file_path):
+    global lines
+    with open(file_path, 'r') as file:
+        lines = file.readlines()
+
+# Function to save audio to a WAV file
+def save_audio_to_file(audio):
+    sample_rate, data = audio  # audio is a tuple (sample_rate, data)
+    
+    # Save the audio data as a WAV file in a temporary location
+    with tempfile.NamedTemporaryFile(delete=False, suffix=".wav") as tmp_file:
+        with wave.open(tmp_file.name, 'wb') as wav_file:
+            wav_file.setnchannels(1)  # Mono audio
+            wav_file.setsampwidth(2)  # 2 bytes per sample (16-bit PCM)
+            wav_file.setframerate(sample_rate)
+            wav_file.writeframes(data.tobytes())
+        
+        # Return the path to the saved WAV file
+        return tmp_file.name
+
+# Function to save data to the Hugging Face dataset
+def save_to_hf_dataset(text, audio_path):
+    with open(audio_path, "rb") as f:
+        audio_data = f.read()
+    hf_writer.save({"text": text, "audio": audio_data})
+
+# Gradio interface function
+def audio_capture_interface():
+    global file_index, line_index, lines
+    
+    # Initial file to read
+    files = os.listdir('./audio_samples')
+    read_lines_from_file(os.path.join('./audio_samples', files[file_index]))
+
+    # Define the interface components
+    audio_input = gr.Audio(source="microphone", type="numpy", label="Speak and click submit")
+    output_text = gr.Textbox(label="Status", placeholder="Status will appear here")
+
+    # Function to capture and process the audio input
+    def process_audio(audio):
+        global line_index, lines
+        
+        try:
+            text_line = lines[line_index].strip()
+            file_path = save_audio_to_file(audio)
+            save_to_hf_dataset(text_line, file_path)
+            return f"Audio saved to {file_path} and uploaded to Hugging Face Dataset."
+        except Exception as e:
+            return f"Error saving audio: {str(e)}"
+
+    # Function to handle navigation buttons
+    def navigate_lines(button):
+        global line_index, lines
+        
+        if button == 'forward':
+            line_index = min(line_index + 1, len(lines) - 1)
+        elif button == 'previous':
+            line_index = max(line_index - 1, 0)
+        
+        output_text.value = lines[line_index]
+
+    # Create the Gradio interface
+    with gr.Blocks() as iface:
+        with gr.Row():
+            gr.Textbox(label="Text", value=lines[line_index], interactive=False)
+        with gr.Row():
+            audio_input.render()
+        with gr.Row():
+            gr.Button("Previous").click(lambda: navigate_lines('previous'), outputs=output_text)
+            gr.Button("Forward").click(lambda: navigate_lines('forward'), outputs=output_text)
+            gr.Button("Submit").click(process_audio, inputs=audio_input, outputs=output_text)
+
+    return iface
+
+# Launch the interface
+iface = audio_capture_interface()
+iface.launch()
+