Create app.py

app.py

@@ -0,0 +1,86 @@
+import json
+import requests
+
+from datetime import datetime
+
+import time
+import traceback
+import gradio as gr # Imports the Gradio library, which is used to create user interfaces for machine learning models.
+
+HF_TOKEN = os.environ.get("HF_TOKEN", None)
+
+def date_now():
+    return datetime.now().strftime("%Y-%m-%d %H:%M:%S")
+    
+def record_opt(msg):
+    return f"{date_now()} {msg}\n"
+    
+def speech_recognize(audio, model_name, opt):
+    opt += record_opt("Transcription starting ...")
+    yield "Transcribing, please wait ...", opt
+    start = time.monotonic()
+
+    with open(audio, "rb") as f:
+        data = f.read()
+    try:
+        url = API_URL + model_name
+        print(f">>> url is {url}")
+        headers = {"Authorization": f"Bearer {HF_TOKEN}"}
+        response = requests.request("POST", url, headers=headers, data=data)
+        text = json.loads(response.content.decode("utf-8"))
+        print(f">>> text is {text}")
+        text = text['text']
+    except:
+        text = f"Transcription failed with error：\n{traceback.format_exc()}"
+
+    cost = time.monotonic() - start
+    opt += record_opt(f"Transcription ends, time consuming {cost:.3f}s")
+    yield text, opt
+
+import gradio as gr
+
+with gr.Blocks() as demo:
+    with gr.Row():
+        with gr.Column():
+            audio = gr.Audio(source="microphone", type="filepath")
+            model_name = gr.Dropdown(
+                label="Models:",
+                choices=[
+                    "openai/whisper-large-v3",
+                    "openai/whisper-large-v2",
+                    "openai/whisper-large",
+                    "openai/whisper-medium",
+                    "openai/whisper-small",
+                    "openai/whisper-base",
+                    "openai/whisper-tiny",
+                ],
+                value="openai/whisper-large-v3",
+            )
+             = gr.Textbox(label="Huggingface token")
+        with gr.Column():
+            output = gr.Textbox(label="Transcription results")
+            operation = gr.Textbox(label="Logging")
+    audio.start_recording(
+        lambda x: x + record_opt("Start recording ..."),
+        inputs=operation, outputs=operation
+    )
+    audio.play(
+        lambda x: x + record_opt("Play recording"),
+        inputs=operation, outputs=operation
+    )
+    audio.pause(
+        lambda x: x + record_opt("Pause playback"),
+        inputs=operation, outputs=operation
+    )
+    audio.stop(
+        lambda x: x + record_opt("Stop playing"),
+        inputs=operation, outputs=operation
+    )
+    audio.end(
+        lambda x: x + record_opt("Finished playing"),
+        inputs=operation, outputs=operation
+    )
+    audio.stop_recording(speech_recognize, inputs=[audio, model_name, operation], outputs=[output, operation])
+
+demo.queue(max_size=4, concurrency_count=4)
+demo.launch()