Spaces:
Runtime error
Runtime error
Update app.py
Browse files
app.py
CHANGED
|
@@ -1,7 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
import gradio as gr
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
|
| 3 |
-
|
| 4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
|
| 6 |
-
demo
|
| 7 |
-
demo.launch()
|
|
|
|
| 1 |
+
import os
|
| 2 |
+
import tempfile
|
| 3 |
+
|
| 4 |
+
import torch
|
| 5 |
import gradio as gr
|
| 6 |
+
from transformers import pipeline
|
| 7 |
+
|
| 8 |
+
|
| 9 |
+
MODEL_NAME = "openai/whisper-large-v3"
|
| 10 |
+
BATCH_SIZE = 8
|
| 11 |
+
|
| 12 |
+
device = 0 if torch.cuda.is_available() else "cpu"
|
| 13 |
+
|
| 14 |
+
pipe = pipeline(
|
| 15 |
+
task="automatic-speech-recognition",
|
| 16 |
+
model=MODEL_NAME,
|
| 17 |
+
chunk_length_s=30,
|
| 18 |
+
device=device,
|
| 19 |
+
)
|
| 20 |
+
|
| 21 |
+
|
| 22 |
+
def transcribe(inputs, task="transcribe"):
|
| 23 |
+
if inputs is None:
|
| 24 |
+
raise gr.Error("No audio file submitted!")
|
| 25 |
+
|
| 26 |
+
output = pipe(
|
| 27 |
+
inputs,
|
| 28 |
+
batch_size=BATCH_SIZE,
|
| 29 |
+
generate_kwargs={"task": task},
|
| 30 |
+
return_timestamps=True
|
| 31 |
+
)
|
| 32 |
+
return output["text"]
|
| 33 |
|
| 34 |
+
demo = gr.Interface(
|
| 35 |
+
fn=transcribe,
|
| 36 |
+
inputs=["audio"],
|
| 37 |
+
outputs="text",
|
| 38 |
+
title="Transcribe Audio to Text", # Give our demo a title
|
| 39 |
+
)
|
| 40 |
|
| 41 |
+
demo.launch()
|
|
|