IBM Watson Website
Link |
|
Create Ressource |
AI -> Visual Recognition |
make service |
Lite Plan |
get important information |
API Key and URL |
Installation
Install opencv |
pip install opencv-python |
Install ibm-watson |
pip install ibm-watson |
Test Application
Send Picture to Goolge press |
d |
Quit application press |
q |
|
|
Paste in a Pythonfile
import cv2
from ibm_watson import VisualRecognitionV3
from ibm_cloud_sdk_core.authenticators import IAMAuthenticator
import json
import sys
authenticator = IAMAuthenticator('API KEY')
service = VisualRecognitionV3(
version='2020-02-26',
authenticator=authenticator
)
service.set_service_url('URL')
cap = cv2.VideoCapture(0)
key = ''
while( key != 'q' ):
ret, frame = cap.read()
cv2.imshow('frame', frame)
intkey = cv2.waitKey(2)
if( intkey > 0 ):
key = chr(intkey)
else:
key = ''
if key == 'd' :
cv2.imwrite('upload.jpg', frame)
with open('upload.jpg','rb') as file:
classes = service.classify(images_file=file,threshold='0.6').get_result()
print(json.dumps(classes, indent=2))
|
Speech to Text
curl -X POST -u "apikey:{apikey}" \
--header "Content-Type: audio/flac" \
--data-binary @{path_to_file}audio-file.flac \
"{url}/v1/recognize?timestamps=true&max_alternatives=3"
|
|
|
Speech to Text
{
"results": [
{
"alternatives": [
{
"timestamps": [
["several":, 1.0, 1.51],
["tornadoes":, 1.51, 2.15],
["touch":, 2.15, 2.5],
. . .
]
},
{
"confidence": 0.96
"transcript": "several tornadoes touch down as a line
of severe thunderstorms swept through Colorado on Sunday "
},
{
"transcript": "several tornadoes touched down as a line of
severe thunderstorms swept through Colorado on Sunday "
},
{
"transcript": "several tornadoes touch down as a line
of severe thunderstorms swept through Colorado and Sunday "
}
],
"final": true
}
],
"result_index": 0
}
|
|