Add torch

app.py

@@ -1,14 +1,25 @@
 import gradio as gr
 from transformers import pipeline
+import torch
 
-pipe = pipeline("automatic-speech-recognition", model="openai/whisper-large-v3")
+MODEL_NAME = "openai/whisper-large-v3"
+BATCH_SIZE = 8
+
+device = 0 if torch.cuda.is_available() else "cpu"
+
+pipe = pipeline(
+    task="automatic-speech-recognition",
+    model=MODEL_NAME,
+    chunk_length_s=30,
+    device=device,
+)
 
 def transcribe(audio):
-  result = pipe(audio)
+  result = pipe(audio, batch_size=BATCH_SIZE)["text"]
   print(result)
 
   return result
 
 app = gr.Interface(transcribe, gr.Audio(sources=["microphone"]), outputs="textbox")
 
-app.launch()
+app.launch(enable_queue=True)

requirements.txt

@@ -43,7 +43,9 @@ MarkupSafe==2.1.5
 matplotlib==3.8.3
 mdurl==0.1.2
 ml-dtypes==0.3.2
+mpmath==1.3.0
 namex==0.0.7
+networkx==3.2.1
 numpy==1.26.4
 opt-einsum==3.3.0
 orjson==3.9.15
@@ -72,6 +74,7 @@ shellingham==1.5.4
 six==1.16.0
 sniffio==1.3.1
 starlette==0.36.3
+sympy==1.12
 tensorboard==2.16.2
 tensorboard-data-server==0.7.2
 tensorflow==2.16.1
@@ -81,6 +84,7 @@ tf_keras==2.16.0
 tokenizers==0.15.2
 tomlkit==0.12.0
 toolz==0.12.1
+torch==2.2.1
 tqdm==4.66.2
 transformers==4.38.2
 typer==0.9.0