first commit
Browse files- app.py +16 -0
- requirements.txt +3 -0
app.py
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import torch
|
2 |
+
import streamlit as st
|
3 |
+
import numpy as np
|
4 |
+
from PIL import Image, ImageDraw
|
5 |
+
from transformers import pipeline
|
6 |
+
from tempfile import NamedTemporaryFile
|
7 |
+
|
8 |
+
audiopipe = pipeline("automatic-speech-recognition", model="openai/whisper-large-v3")st.title('Upload an audio file for speech recognition')
|
9 |
+
|
10 |
+
uploaded_audio_file = st.file_uploader("Choose an audio file (wav)")
|
11 |
+
if uploaded_audio_file is not None:
|
12 |
+
with NamedTemporaryFile(suffix="wav") as temp:
|
13 |
+
temp.write(uploaded_audio_file.getvalue())
|
14 |
+
temp.seek(0)
|
15 |
+
result = audiopipe(temp.name)
|
16 |
+
st.write(result)
|
requirements.txt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
streamlit
|
2 |
+
accelerate
|
3 |
+
transformers
|