Update app.py

app.py

@@ -1,10 +1,8 @@
 import torch
-
 import gradio as gr
 import yt_dlp as youtube_dl
 from transformers import pipeline
 from transformers.pipelines.audio_utils import ffmpeg_read
-
 import tempfile
 import os
 
@@ -22,7 +20,6 @@ pipe = pipeline(
     device=device,
 )
 
-
 def transcribe(microphone, file_upload, task):
     warn_output = ""
     if (microphone is not None) and (file_upload is not None):
@@ -34,19 +31,18 @@ def transcribe(microphone, file_upload, task):
     elif (microphone is None) and (file_upload is None):
         raise gr.Error("You have to either use the microphone or upload an audio file")
 
-    file_size_mb = os.stat(inputs).st_size / (1024 * 1024)
+    file = microphone if microphone is not None else file_upload
+    file_size_mb = os.stat(file).st_size / (1024 * 1024)
     if file_size_mb > FILE_LIMIT_MB:
         raise gr.Error(
-                f"File size exceeds file size limit. Got file of size {file_size_mb:.2f}MB for a limit of {FILE_LIMIT_MB}MB."
+            f"File size exceeds file size limit. Got file of size {file_size_mb:.2f}MB for a limit of {FILE_LIMIT_MB}MB."
         )
 
-    file = microphone if microphone is not None else file_upload
-
-    text = pipe(file, batch_size=BATCH_SIZE, generate_kwargs={"task": task})["text"]
+    text = pipe(file, batch_size=BATCH_SIZE,
+                generate_kwargs={"task": task})["text"]
 
     return warn_output + text
 
-
 def _return_yt_html_embed(yt_url):
     video_id = yt_url.split("?v=")[-1]
     HTML_str = (
@@ -61,18 +57,9 @@ def download_yt_audio(yt_url, filename):
         info = info_loader.extract_info(yt_url, download=False)
     except youtube_dl.utils.DownloadError as err:
         raise gr.Error(str(err))
-    file_length = info["duration_string"]
-    file_h_m_s = file_length.split(":")
-    file_h_m_s = [int(sub_length) for sub_length in file_h_m_s]
-    if len(file_h_m_s) == 1:
-        file_h_m_s.insert(0, 0)
-    if len(file_h_m_s) == 2:
-        file_h_m_s.insert(0, 0)
-    file_length_s = file_h_m_s[0] * 3600 + file_h_m_s[1] * 60 + file_h_m_s[2]
+    file_length_s = info.get('duration', 0)
     if file_length_s > YT_LENGTH_LIMIT_S:
-        yt_length_limit_hms = time.strftime("%HH:%MM:%SS", time.gmtime(YT_LENGTH_LIMIT_S))
-        file_length_hms = time.strftime("%HH:%MM:%SS", time.gmtime(file_length_s))
-        raise gr.Error(f"Maximum YouTube length is {yt_length_limit_hms}, got {file_length_hms} YouTube video.")
+        raise gr.Error(f"Maximum YouTube length is {YT_LENGTH_LIMIT_S} seconds, got {file_length_s} seconds YouTube video.")
     ydl_opts = {"outtmpl": filename, "format": "worstvideo[ext=mp4]+bestaudio[ext=m4a]/best[ext=mp4]/best"}
     with youtube_dl.YoutubeDL(ydl_opts) as ydl:
         try:
@@ -80,7 +67,6 @@ def download_yt_audio(yt_url, filename):
         except youtube_dl.utils.ExtractorError as err:
             raise gr.Error(str(err))
 
-
 def yt_transcribe(yt_url, task, max_filesize=75.0):
     html_embed_str = _return_yt_html_embed(yt_url)
 
@@ -93,11 +79,10 @@ def yt_transcribe(yt_url, task, max_filesize=75.0):
     inputs = ffmpeg_read(inputs, pipe.feature_extractor.sampling_rate)
     inputs = {"array": inputs, "sampling_rate": pipe.feature_extractor.sampling_rate}
 
-    text = pipe(inputs, batch_size=BATCH_SIZE, generate_kwargs={"task": task})["text"]
+    text = pipe(inputs, batch_size=BATCH_SIZE,    generate_kwargs={"task": task})["text"]
 
     return html_embed_str, text
 
-
 demo = gr.Blocks()
 
 mf_transcribe = gr.Interface(
@@ -140,5 +125,4 @@ yt_transcribe = gr.Interface(
 with demo:
     gr.TabbedInterface([mf_transcribe, yt_transcribe], ["Transcribe Audio", "Transcribe YouTube"])
 
-demo.launch(enable_queue=True)
-
+demo.launch(enable_queue=True)