new

app copy 2.py

@@ -0,0 +1,57 @@
+import gradio as gr
+import speech_recognition as sr
+import os
+
+def transcribe_audio(file_path):
+    """Transcribes audio to text using the speech_recognition library."""
+    recognizer = sr.Recognizer()
+    with sr.AudioFile(file_path) as source:
+        audio_data = recognizer.record(source)
+    try:
+        text = recognizer.recognize_google(audio_data)
+        return text
+    except sr.UnknownValueError:
+        return "Google Speech Recognition could not understand audio"
+    except sr.RequestError as e:
+        return f"Could not request results from Google Speech Recognition service; {e}"
+
+def handle_transcription(file_info):
+    """Handle transcription after recording."""
+    if file_info is None:
+        return f" 111 No audio recorded or file not found:  {file_info}"
+    print (file_info)
+    file_path = file_info
+    if os.path.exists(file_path):
+        return transcribe_audio(file_path)
+    return f"222 No audio recorded or file not found: {file_info}"
+
+with gr.Blocks() as demo:
+    gr.Markdown("### Voice Recorder and Transcriber")
+    audio_box = gr.Audio(label="Record Audio", sources="microphone", type="filepath", elem_id='audio')
+
+    with gr.Row():
+        record_btn = gr.Button('Record/Stop')
+        transcribe_btn = gr.Button('Transcribe')
+
+    output_text = gr.Textbox(label="Transcription Output")
+
+    def manage_record(recording_state):
+        """Toggle recording and manage UI updates."""
+        return not recording_state, "Stop" if not recording_state else "Record"
+
+    state = gr.State(False)  # False indicates not recording, True indicates recording
+
+    record_btn.click(
+        fn=manage_record,
+        inputs=state,
+        outputs=[state, record_btn],
+        js="document.getElementById('audio').value = null; document.getElementById('audio').click();"
+    )
+
+    transcribe_btn.click(
+        fn=handle_transcription,
+        inputs=audio_box,
+        outputs=output_text
+    )
+
+demo.launch(debug=True)

app copy 3.py

@@ -0,0 +1,53 @@
+import gradio as gr
+import speech_recognition as sr
+import os
+
+def transcribe_audio(file_path):
+    """Transcribes audio to text using the speech_recognition library."""
+    recognizer = sr.Recognizer()
+    with sr.AudioFile(file_path) as source:
+        audio_data = recognizer.record(source)
+    try:
+        text = recognizer.recognize_google(audio_data)
+        return text
+    except sr.UnknownValueError:
+        return "Google Speech Recognition could not understand audio"
+    except sr.RequestError as e:
+        return f"Could not request results from Google Speech Recognition service; {e}"
+
+def handle_transcription(file_info):
+    """Handle transcription after recording."""
+    if file_info is None:
+        return "No audio recorded or file not found."
+    file_path = file_info
+    if os.path.exists(file_path):
+        return transcribe_audio(file_path)
+    return "No audio recorded or file not found."
+
+with gr.Blocks() as demo:
+    gr.Markdown("### Voice Recorder and Transcriber")
+    audio_box = gr.Audio(label="Record Audio", type="filepath", elem_id='audio')
+
+    with gr.Row():
+        record_btn = gr.Button('Record')
+        transcribe_btn = gr.Button('Transcribe')
+
+    output_text = gr.Textbox(label="Transcription Output")
+
+    def toggle_record(button_text):
+        """Toggle the button text and manage the recording."""
+        return "Stop" if button_text == "Record" else "Record"
+
+    record_btn.click(
+        fn=toggle_record,
+        inputs=record_btn,
+        outputs=record_btn
+    )
+
+    transcribe_btn.click(
+        fn=handle_transcription,
+        inputs=audio_box,
+        outputs=output_text
+    )
+
+demo.launch(debug=True)

app copy 4.py

@@ -0,0 +1,64 @@
+import gradio as gr
+import speech_recognition as sr
+import os
+
+def transcribe_audio(file_path):
+    """Transcribes audio to text using the speech_recognition library."""
+    recognizer = sr.Recognizer()
+    with sr.AudioFile(file_path) as source:
+        audio_data = recognizer.record(source)
+    try:
+        text = recognizer.recognize_google(audio_data)
+        return text
+    except sr.UnknownValueError:
+        return "Google Speech Recognition could not understand audio"
+    except sr.RequestError as e:
+        return f"Could not request results from Google Speech Recognition service; {e}"
+
+def handle_transcription(file_info):
+    """Handle transcription after recording."""
+    if file_info is None:
+        return "No audio recorded or file not found."
+    file_path = file_info
+    if os.path.exists(file_path):
+        return transcribe_audio(file_path)
+    return "No audio recorded or file not found."
+
+with gr.Blocks() as demo:
+    gr.Markdown("### Voice Recorder and Transcriber")
+    audio_box = gr.Audio(label="Record Audio",  sources="microphone", type="filepath", elem_id='audio')
+
+    with gr.Row():
+        record_btn = gr.Button('Record')
+        transcribe_btn = gr.Button('Transcribe')
+
+    output_text = gr.Textbox(label="Transcription Output")
+
+    def create_toggle_record(record_btn):
+        print(111)
+        def toggle_record( button_text):
+            if button_text == "Record":
+                print(222)
+                print(audio_box)
+                audio_box.start_recording()
+                return "Stop"  # Return new button text (Stop)
+            else:
+                audio_box.stop_recording()
+                return "Record"  # Return new button text (Record)
+        return toggle_record
+
+    # Create the closure and connect it to the button click
+    toggle_record_fn = create_toggle_record(record_btn)
+    record_btn.click(
+        fn=toggle_record_fn,
+        inputs=[record_btn],  # Pass only the button (no need for text)
+        outputs=record_btn
+    )
+
+    transcribe_btn.click(
+        fn=handle_transcription,
+        inputs=audio_box,
+        outputs=output_text
+    )
+
+demo.launch(debug=True)

app copy 5.py

@@ -0,0 +1,59 @@
+import gradio as gr
+import time
+import speech_recognition as sr
+
+def transcribe(audio):
+    if audio is None:
+        return "No audio recorded."
+    
+    recognizer = sr.Recognizer()
+    with sr.AudioFile(audio) as source:
+        audio_data = recognizer.record(source)
+    try:
+        text = recognizer.recognize_google(audio_data)
+        return text
+    except sr.UnknownValueError:
+        return "Google Speech Recognition could not understand audio"
+    except sr.RequestError as e:
+        return f"Could not request results from Google Speech Recognition service; {e}"
+
+def toggle_recording(audio, state):
+    if state == "Idle":
+        return None, "Recording", "Recording... Click 'Stop' when finished."
+    else:
+        time.sleep(1)  # Small delay to ensure audio is processed
+        if audio is not None:
+            transcription = transcribe(audio)
+            return None, "Idle", transcription
+        else:
+            return None, "Idle", "No audio recorded."
+
+with gr.Blocks() as demo:
+    audio = gr.Audio(sources="microphone", type="filepath", elem_id="audio-component")
+    button = gr.Button("Record", elem_id="record-button")
+    state = gr.State("Idle")
+    output = gr.Textbox(label="Transcription")
+
+    button.click(
+        fn=toggle_recording,
+        inputs=[audio, state],
+        outputs=[audio, state, output],
+        js="""
+        async (audio, state) => {
+            const audioEl = document.querySelector('#audio-component audio');
+            const recordButton = document.querySelector('#record-button');
+            
+            if (state === "Idle") {
+                await audio.startRecording();
+                recordButton.textContent = "Stop";
+                return [null, "Recording", "Recording... Click 'Stop' when finished."];
+            } else {
+                await audio.stopRecording();
+                recordButton.textContent = "Record";
+                return [await audio.getValue(), "Idle", "Processing..."];
+            }
+        }
+        """
+    )
+
+demo.queue().launch(debug=True)

app copy 6.py

@@ -0,0 +1,47 @@
+import gradio as gr
+
+def click_js():
+    return """
+    function(audio_btn, update_status) {
+        const recordBtn = document.querySelector('#audio button');
+        if (audio_btn == 'Speak') {
+            recordBtn.click();  // Start recording
+            update_status('Stop');  // Update the button to show 'Stop'
+            return 'Recording...';
+        } else {
+            recordBtn.click();  // Stop recording
+            update_status('Speak');  // Reset button text
+            return new Promise(resolve => {
+                setTimeout(() => {  // Wait a small delay to ensure recording has stopped
+                    resolve('Done recording');
+                }, 500);
+            });
+        }
+    }
+    """
+
+def transcribe(recording_status):
+    if recording_status == 'Done recording':
+        print('Transcribing...')
+        return 'Success'
+    else:
+        return recording_status
+
+with gr.Blocks() as demo:
+    msg = gr.Textbox()
+    audio_box = gr.Audio(label="Audio", sources="microphone", type="filepath", elem_id='audio')
+
+    with gr.Row():
+        audio_btn = gr.Button('Speak')
+        clear = gr.Button("Clear")
+
+    audio_btn.click(
+        js=click_js(), 
+        inputs=[audio_btn], 
+        outputs=[audio_btn, msg], 
+        fn=transcribe
+    )
+
+    clear.click(lambda: "", inputs=None, outputs=msg, queue=False)
+
+demo.launch(debug=True)

app copy.py

@@ -0,0 +1,56 @@
+import gradio as gr
+import speech_recognition as sr
+from pprint import pprint as pp
+import os
+
+def transcribe_audio(file_path):
+    """Transcribes audio to text using the speech_recognition library."""
+    recognizer = sr.Recognizer()
+    with sr.AudioFile(file_path) as source:
+        audio_data = recognizer.record(source)
+    try:
+        # Using Google's speech recognition service. Note: It requires internet.
+        text = recognizer.recognize_google(audio_data)
+        return text
+    except sr.UnknownValueError:
+        return "Google Speech Recognition could not understand audio"
+    except sr.RequestError as e:
+        return f"Could not request results from Google Speech Recognition service; {e}"
+
+def manage_record():
+    """Toggle recording and manage UI updates."""
+    js_code = """
+    const btn = document.getElementById('record_btn');
+    const recordingText = 'Stop';
+    const idleText = 'Record';
+    if (btn.textContent.includes(idleText)) {
+        btn.textContent = recordingText;
+    } else {
+        btn.textContent = idleText;
+    }
+    """
+    return gr.update(js=js_code)
+
+def handle_transcription(file_info):
+    """Handle transcription after recording."""
+    print(file_info)
+    file_path = file_info
+    print(file_path )
+    if os.path.exists(file_path):
+        return transcribe_audio(file_path)
+    return "No audio recorded or file not found."
+
+with gr.Blocks() as demo:
+    gr.Markdown("### Voice Recorder and Transcriber")
+    audio_box = gr.Audio(label="Record Audio", sources="microphone", type="filepath", elem_id='audio')
+
+    with gr.Row():
+        record_btn = gr.Button('Record/Stop', elem_id='record_btn')
+        transcribe_btn = gr.Button('Transcribe')
+
+    output_text = gr.Textbox(label="Transcription Output")
+
+    record_btn.click(fn=manage_record)
+    transcribe_btn.click(fn=handle_transcription, inputs=audio_box, outputs=output_text)
+
+demo.launch(debug=True)

app.py

@@ -0,0 +1,21 @@
+import gradio as gr
+from transformers import pipeline
+import numpy as np
+
+transcriber = pipeline("automatic-speech-recognition", model="openai/whisper-base.en")
+
+def transcribe(audio):
+    sr, y = audio
+    y = y.astype(np.float32)
+    y /= np.max(np.abs(y))
+
+    return transcriber({"sampling_rate": sr, "raw": y})["text"]
+
+
+demo = gr.Interface(
+    transcribe,
+    gr.Audio(sources=["microphone"]),
+    "text",
+)
+
+demo.launch()

push.bat

@@ -0,0 +1,3 @@
+git add .
+git commit -m "%1"
+git push