up

run_demo.py

@@ -1,14 +1,29 @@
-import torch
+import logging
+import warnings
 
 import gradio as gr
 import pytube as pt
-from transformers import pipeline
+import torch
 from huggingface_hub import model_info
+from transformers import pipeline
+from transformers.utils.logging import disable_progress_bar
+
+warnings.filterwarnings("ignore")
+disable_progress_bar()
 
-MODEL_NAME = "bofenghuang/whisper-medium-cv11-french"
+MODEL_NAME = "bofenghuang/whisper-large-v2-cv11-french"
 CHUNK_LENGTH_S = 30
 
+logging.basicConfig(
+    format="%(asctime)s [%(levelname)s] [%(name)s] %(message)s",
+    datefmt="%Y-%m-%dT%H:%M:%SZ",
+)
+logger = logging.getLogger(__name__)
+logger.setLevel(logging.DEBUG)
+
 device = 0 if torch.cuda.is_available() else "cpu"
+logger.info(f"Model will be loaded on device `{device}`")
+
 pipe = pipeline(
     task="automatic-speech-recognition",
     model=MODEL_NAME,
@@ -33,6 +48,8 @@ def transcribe(microphone, file_upload):
 
     text = pipe(file)["text"]
 
+    logger.info(f"Transcription: {text}")
+
     return warn_output + text
 
 
@@ -53,6 +70,8 @@ def yt_transcribe(yt_url):
 
     text = pipe("audio.mp3")["text"]
 
+    logger.info(f'Transcription of "{yt_url}": {text}')
+
     return html_embed_str, text
 
 
@@ -61,10 +80,11 @@ demo = gr.Blocks()
 mf_transcribe = gr.Interface(
     fn=transcribe,
     inputs=[
-        gr.inputs.Audio(source="microphone", type="filepath", optional=True),
-        gr.inputs.Audio(source="upload", type="filepath", optional=True),
+        gr.inputs.Audio(source="microphone", type="filepath", optional=True, label="Record"),
+        gr.inputs.Audio(source="upload", type="filepath", optional=True, label="Upload File"),
     ],
-    outputs="text",
+    # outputs="text",
+    outputs=gr.outputs.Textbox(label="Transcription"),
     layout="horizontal",
     theme="huggingface",
     title="Whisper French Demo 🇫🇷 : Transcribe Audio",
@@ -79,7 +99,11 @@ mf_transcribe = gr.Interface(
 yt_transcribe = gr.Interface(
     fn=yt_transcribe,
     inputs=[gr.inputs.Textbox(lines=1, placeholder="Paste the URL to a YouTube video here", label="YouTube URL")],
-    outputs=["html", "text"],
+    # outputs=["html", "text"],
+    outputs=[
+        gr.outputs.HTML(label="YouTube Page"),
+        gr.outputs.Textbox(label="Transcription"),
+    ],
     layout="horizontal",
     theme="huggingface",
     title="Whisper French Demo 🇫🇷 : Transcribe YouTube",
@@ -94,4 +118,5 @@ yt_transcribe = gr.Interface(
 with demo:
     gr.TabbedInterface([mf_transcribe, yt_transcribe], ["Transcribe Audio", "Transcribe YouTube"])
 
+# demo.launch(server_name="0.0.0.0", debug=True, share=True)
 demo.launch(enable_queue=True)