app.py

#!/usr/bin/env python3
#
# Copyright      2022  Xiaomi Corp.        (authors: Fangjun Kuang)
#
# See LICENSE for clarification regarding multiple authors
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

import gradio as gr

demo = gr.Blocks()


def process_uploaded_file(uploaded_file: str):
    print("uploaded_file", uploaded_file)
    return "hello"


with demo:
    gr.Markdown("Upload audio from disk or record from microphone for recognition")
    with gr.Tabs():
        with gr.TabItem("Upload from disk"):
            uploaded_file = gr.inputs.Audio(
                source="upload",  # Choose between "microphone", "upload"
                type="filepath",
                optional=False,
                label="Upload from disk",
            )
            upload_button = gr.Button("Upload")
            uploaded_output = (
                gr.outputs.Textbox(label="Recognized speech for uploaded file"),
            )

        with gr.TabItem("Record from microphone"):
            microphone = gr.inputs.Audio(
                source="microphone",  # Choose between "microphone", "upload"
                type="filepath",
                optional=False,
                label="Record from microphone",
            )
            recorded_output = (
                gr.outputs.Textbox(label="Recognized speech for recordings"),
            )

            record_button = gr.Button("Record")

        upload_button.click(
            process_uploaded_file,
            inputs=uploaded_file,
            outputs=uploaded_output,
        )
        record_button.click(
            process_uploaded_file,
            inputs=microphone,
            outputs=recorded_output,
        )

if __name__ == "__main__":
    demo.launch()