Functional improvement of an existing SWIFT app

General information for the business: We develope mobile applications
Kind of development: Customization of existing program
Description of requirements/functionality: There is a feature where you can upload an audio clip to the app and then send it to the server in two-second parts. This function does not work properly. The app shows an incorrect result. When I upload a 6-minute audio clip to the app, it shows that men and women have talked 12 minutes total. This is not correct because the audio clip that i have uploaded to the app is just 6 minutes.
You need to fix the function so the app sends all the data (all two-second sound clips) to the server and then analyze all the results and displays the correct result to the user.
We do not know where the problem lies. If it is in the application or the server. You must find out where the problem is and fix so the app can send and analyzes the entire audio clip.

Case senario (this is how the function should work):
User presses ”Settings”
Turns on the ”split audio into two-second segment ”
User presses ”uploaded video”
Drags a 5-6 minute long audio clip to the app
Presses ”star analysis”
The App sends data (two-second audio chunks) to the server
Receiving a response from the server and analyzes how much men / women spoke
The app stops when the entire audio clip has been sent to the server and all results from server has been analyzed and shown to the user.
Specific technologies required: Swift Xcode
Extra notes: Background
We need to fix an existing iOS App. It is in practice complete and written in Swift. It records audio clips, and then sends it to a backend server. The server analyzes the audio clip and
send the results back to the app. The result is then displayed to the user. The server analyzes the
sound clip, and produce how many times and for how long female / male speakers talk on the
sound clip.

What is done?
The backend server is ready and running on Google Cloud. You can record audio clips and upload audio clips to the app. You can choose to split the audio clips and send them in chunks to the server. The app is basically completed.

What needs to be done?
There is a feature where you can upload an audio clip to the app and then send it to the server in two-second parts. This function does not work properly. The app shows an incorrect result. When I upload a 6-minute audio clip to the app, it shows that men and women have talked 12 minutes total. This is not correct because the audio clip that i have uploaded to the app is just 6 minutes.
You need to fix the function so the app sends all the data (all two-second sound clips) to the server and then analyze all the results and displays the correct result to the user.
We do not know where the problem lies. If it is in the application or the server. You must find out where the problem is and fix so the app can send and analyzes the entire audio clip.

Case senario (this is how the function should work):
User presses ”Settings”
Turns on the ”split audio into two-second segment ”
User presses ”uploaded video”
Drags a 5-6 minute long audio clip to the app
Presses ”star analysis”
The App sends data (two-second audio chunks) to the server
Receiving a response from the server and analyzes how much men / women spoke
The app stops when the entire audio clip has been sent to the server and all results from server has been analyzed and shown to the user.

Resources
The code for the app is available here: https://www.dropbox.com/s/njiuztbqpu51fts/
GenderTimer3.0.zip?dl=0

Audio file for testing: https://www.dropbox.com/s/bmjkbp5b4bfe95a/6%20minute%20audio.aifc?
dl=0

The result from the server is in JSON format and looks like this:
{"duration": 2186, "url": "tmp/upload_148b0446d7320b58e80c1c748eb5cbd7.wav", "db": "/
root/.voiceid/gmm_db", "selections": [{"speakers": {}, "speakerLabel": "S1", "gender": "F",
"speaker": "unknown", "startTime": 15.54, "endTime": 21.91}, {"speakers": {}, "speakerLabel": "S0",
"gender": "M", "speaker": "unknown", "startTime": 0.0, "endTime": 15.49}]}