SPI reliability problem when transferring large amount of data

I'm building SPI slave based on STM32F750V8T6 MCU and I'm having problem loosing sync between master and slave. When I run test that is sending sync bytes, slave receive data from master, sync again and slave is returning data after some time master ends up receiving sync bytes not the message that has been sent.

I have tried lowering speed, adding delays between syncs.

Master SPI config:

 hspi1.Instance = SPI1;
 hspi1.Init.Mode = SPI_MODE_MASTER;
 hspi1.Init.Direction = SPI_DIRECTION_2LINES;
 hspi1.Init.DataSize = SPI_DATASIZE_8BIT;
 hspi1.Init.CLKPolarity = SPI_POLARITY_LOW;
 hspi1.Init.CLKPhase = SPI_PHASE_1EDGE;
 hspi1.Init.NSS = SPI_NSS_SOFT;
 hspi1.Init.BaudRatePrescaler = SPI_BAUDRATEPRESCALER_4;
 hspi1.Init.FirstBit = SPI_FIRSTBIT_MSB;
 hspi1.Init.TIMode = SPI_TIMODE_DISABLE;
 hspi1.Init.CRCCalculation = SPI_CRCCALCULATION_DISABLE;
 hspi1.Init.CRCPolynomial = 7;
 hspi1.Init.CRCLength = SPI_CRC_LENGTH_DATASIZE;
 hspi1.Init.NSSPMode = SPI_NSS_PULSE_ENABLE;
 if (HAL_SPI_Init(&hspi1) != HAL_OK)
 {
 Error_Handler();
 }

slave SPI init

 hspi1.Instance = SPI1;
 hspi1.Init.Mode = SPI_MODE_SLAVE;
 hspi1.Init.Direction = SPI_DIRECTION_2LINES;
 hspi1.Init.DataSize = SPI_DATASIZE_8BIT;
 hspi1.Init.CLKPolarity = SPI_POLARITY_LOW;
 hspi1.Init.CLKPhase = SPI_PHASE_1EDGE;
 hspi1.Init.NSS = SPI_NSS_SOFT;
 hspi1.Init.FirstBit = SPI_FIRSTBIT_MSB;
 hspi1.Init.TIMode = SPI_TIMODE_DISABLE;
 hspi1.Init.CRCCalculation = SPI_CRCCALCULATION_DISABLE;
 hspi1.Init.CRCPolynomial = 7;
 hspi1.Init.CRCLength = SPI_CRC_LENGTH_DATASIZE;
 hspi1.Init.NSSPMode = SPI_NSS_PULSE_DISABLE;
 if (HAL_SPI_Init(&hspi1) != HAL_OK)
 {
 Error_Handler();
 }

master sync

uint8_t txackbytes = SPI_MASTER_SYNBYTE;
 rxackbytes = 0x00;
 do
 {
 SPI_TASK(HAL_SPI_TransmitReceive(&hspi1, (uint8_t *)&txackbytes, (uint8_t *)&rxackbytes, 1, HAL_MAX_DELAY))
 }while(rxackbytes != SPI_SLAVE_SYNBYTE);

slave sync

 uint8_t txackbyte = SPI_SLAVE_SYNBYTE;
 uint8_t rxackbyte = 0x00;
 do
 {
 SPI_TASK(HAL_SPI_TransmitReceive(&hspi1, (uint8_t *)&txackbyte, (uint8_t *)&rxackbyte, 1, HAL_MAX_DELAY))
 } while (rxackbyte != SPI_MASTER_SYNBYTE);

master while(1)

HAL_GPIO_WritePin(SPI_SS_GPIO_Port,SPI_SS_Pin,GPIO_PIN_RESET);
 
 Master_Synchro();
 SPI_TASK(HAL_SPI_Transmit(&hspi1, (uint8_t*)&porukaSize, 2, 50));
 
 Master_Synchro();
 SPI_TASK(HAL_SPI_Transmit(&hspi1, poruka, porukaSize, 50));
 
 Master_Synchro();
 SPI_TASK(HAL_SPI_Receive(&hspi1, aRxBuffer, porukaSize, 50));
 
 HAL_GPIO_WritePin(SPI_SS_GPIO_Port,SPI_SS_Pin,GPIO_PIN_SET);
 
 if(strcmp(poruka, aRxBuffer) != 0)
 flag = 0;
 
 if (flag){
 broj_uspeha++;
 }
 memset(aRxBuffer, 0, sizeof(aRxBuffer));

slave while(1)

if(!HAL_GPIO_ReadPin(SPI_SS_GPIO_Port,SPI_SS_Pin)){
 
 Slave_Synchro();
 SPI_TASK(HAL_SPI_Receive(&hspi1, (uint8_t*)&aRxBufferSize, 2, 50));
 
 Slave_Synchro();
 SPI_TASK(HAL_SPI_Receive(&hspi1, aRxBuffer, aRxBufferSize, 50));
 
 memcpy(aTxBuffer, aRxBuffer, sizeof(aRxBuffer));
 
 Slave_Synchro();
 SPI_TASK(HAL_SPI_Transmit(&hspi1, aTxBuffer, aRxBufferSize, 50));
 
 memset(aRxBuffer, 0, sizeof(aRxBuffer));
 memset(aTxBuffer, 0, sizeof(aTxBuffer));
 }