SPI code for STM32F446RE

I have been working on the SPI port of STM32F446RE. I am using (MDK Version 5 - Keil) as the IDE. I have configured my device to use the SPI1 port of the device. All the configuration details are as follows.

Mode: Full-duplex Master
Data size: 8 bits
First bit: MSB First
Prescaler: 32,
that corresponds to a baud rate of 2.625MBits/s
Clock Polarity: Low
Clock Phase: 1 Edge

I want to transmit {1,1,0,1,0,1} from MOSI(Master out slave in).

The code, I have written is-

#include "main.h"


SPI_HandleTypeDef hspi1;
SPI_HandleTypeDef hspi3;


void SystemClock_Config(void);
static void MX_GPIO_Init(void);
static void MX_SPI1_Init(void);
static void MX_SPI3_Init(void);


uint8_t receivedbyte[6]= {1,1,0,1,0,1};
int rx_buffer ='C';
uint8_t data[16]={0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0};



int main(void)
{
  HAL_Init();
  SystemClock_Config();

  MX_GPIO_Init();
  MX_SPI1_Init();
  MX_SPI3_Init();

  while (1)
  {
HAL_GPIO_WritePin(GPIOA, GPIO_PIN_4, GPIO_PIN_SET);
HAL_Delay(1000);
HAL_SPI_Transmit(&hspi1, (uint8_t*) receivedbyte ,6, 0x04);
HAL_Delay(1000);
HAL_GPIO_WritePin(GPIOA, GPIO_PIN_4, GPIO_PIN_SET);

  }

}


void SystemClock_Config(void)
{
  RCC_OscInitTypeDef RCC_OscInitStruct = {0};
  RCC_ClkInitTypeDef RCC_ClkInitStruct = {0};


  __HAL_RCC_PWR_CLK_ENABLE();
  __HAL_PWR_VOLTAGESCALING_CONFIG(PWR_REGULATOR_VOLTAGE_SCALE3);

  RCC_OscInitStruct.OscillatorType = RCC_OSCILLATORTYPE_HSI;
  RCC_OscInitStruct.HSIState = RCC_HSI_ON;
  RCC_OscInitStruct.HSICalibrationValue = RCC_HSICALIBRATION_DEFAULT;
  RCC_OscInitStruct.PLL.PLLState = RCC_PLL_ON;
  RCC_OscInitStruct.PLL.PLLSource = RCC_PLLSOURCE_HSI;
  RCC_OscInitStruct.PLL.PLLM = 16;
  RCC_OscInitStruct.PLL.PLLN = 336;
  RCC_OscInitStruct.PLL.PLLP = RCC_PLLP_DIV4;
  RCC_OscInitStruct.PLL.PLLQ = 2;
  RCC_OscInitStruct.PLL.PLLR = 2;
  if (HAL_RCC_OscConfig(&RCC_OscInitStruct) != HAL_OK)
  {
    Error_Handler();
  }

  RCC_ClkInitStruct.ClockType = RCC_CLOCKTYPE_HCLK|RCC_CLOCKTYPE_SYSCLK
                              |RCC_CLOCKTYPE_PCLK1|RCC_CLOCKTYPE_PCLK2;
  RCC_ClkInitStruct.SYSCLKSource = RCC_SYSCLKSOURCE_PLLCLK;
  RCC_ClkInitStruct.AHBCLKDivider = RCC_SYSCLK_DIV1;
  RCC_ClkInitStruct.APB1CLKDivider = RCC_HCLK_DIV2;
  RCC_ClkInitStruct.APB2CLKDivider = RCC_HCLK_DIV1;

  if (HAL_RCC_ClockConfig(&RCC_ClkInitStruct, FLASH_LATENCY_2) != HAL_OK)
  {
    Error_Handler();
  }
}


static void MX_SPI1_Init(void)
{ 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_HARD_OUTPUT;
  hspi1.Init.BaudRatePrescaler = SPI_BAUDRATEPRESCALER_64;
  hspi1.Init.FirstBit = SPI_FIRSTBIT_MSB;
  hspi1.Init.TIMode = SPI_TIMODE_DISABLE;
  hspi1.Init.CRCCalculation = SPI_CRCCALCULATION_DISABLE;
  hspi1.Init.CRCPolynomial = 10;
  if (HAL_SPI_Init(&hspi1) != HAL_OK)
  {
    Error_Handler();
  }

}
static void MX_SPI3_Init(void)
{
  hspi3.Instance = SPI3;
  hspi3.Init.Mode = SPI_MODE_MASTER;
  hspi3.Init.Direction = SPI_DIRECTION_2LINES;
  hspi3.Init.DataSize = SPI_DATASIZE_8BIT;
  hspi3.Init.CLKPolarity = SPI_POLARITY_LOW;
  hspi3.Init.CLKPhase = SPI_PHASE_1EDGE;
  hspi3.Init.NSS = SPI_NSS_SOFT;
  hspi3.Init.BaudRatePrescaler = SPI_BAUDRATEPRESCALER_32;
  hspi3.Init.FirstBit = SPI_FIRSTBIT_MSB;
  hspi3.Init.TIMode = SPI_TIMODE_DISABLE;
  hspi3.Init.CRCCalculation = SPI_CRCCALCULATION_DISABLE;
  hspi3.Init.CRCPolynomial = 10;
  if (HAL_SPI_Init(&hspi3) != HAL_OK)
  {
    Error_Handler();
  }
}
static void MX_GPIO_Init(void)
{
  GPIO_InitTypeDef GPIO_InitStruct = {0};


  __HAL_RCC_GPIOA_CLK_ENABLE();
  __HAL_RCC_GPIOC_CLK_ENABLE();
  __HAL_RCC_GPIOB_CLK_ENABLE();


  HAL_GPIO_WritePin(GPIOC, GPIO_PIN_4, GPIO_PIN_RESET);


  GPIO_InitStruct.Pin = GPIO_PIN_4;
  GPIO_InitStruct.Mode = GPIO_MODE_OUTPUT_PP;
  GPIO_InitStruct.Pull = GPIO_NOPULL;
  GPIO_InitStruct.Speed = GPIO_SPEED_FREQ_LOW;
  HAL_GPIO_Init(GPIOC, &GPIO_InitStruct);

}
void Error_Handler(void)
{

}

#ifdef  USE_FULL_ASSERT

void assert_failed(uint8_t *file, uint32_t line)
{

}
#endif /* USE_FULL_ASSERT */

I am receiving the required data but each data is coming after 8 pulses. there is gap of 7 clock pulse between each data point.