| Method |
Description |
Parameter |
Parameter Type |
Parameter Description |
Default Value |
print() |
Print the result to the terminal |
format_json |
bool |
Whether to format the output content using JSON indentation |
True |
indent |
int |
Specify the indentation level to beautify the output JSON data, making it more readable. Effective only when format_json is True |
4 |
ensure_ascii |
bool |
Control whether to escape non-ASCII characters to Unicode. When set to True, all non-ASCII characters will be escaped; False will retain the original characters. Effective only when format_json is True |
False |
save_to_json() |
Save the result as a JSON file |
save_path |
str |
Path to save the file. When it is a directory, the saved file name is consistent with the input file type naming |
None |
indent |
int |
Specify the indentation level to beautify the output JSON data, making it more readable. Effective only when format_json is True |
4 |
ensure_ascii |
bool |
Control whether to escape non-ASCII characters to Unicode. When set to True, all non-ASCII characters will be escaped; False will retain the original characters. Effective only when format_json is True |
False |
- Calling the `print()` method will print the result to the terminal, with the printed content explained as follows:
- `input_path`: The path where the input audio is stored
- `result`: Recognition result
- `text`: The text result of speech recognition
- `segments`: The result text with timestamps
* `id`: ID
* `seek`: Audio segment pointer
* `start`: Segment start time
* `end`: Segment end time
* `text`: Text recognized in the segment
* `tokens`: Token IDs of the segment text
* `temperature`: Speed variation ratio
* `avg_logprob`: Average log probability
* `compression_ratio`: Compression ratio
* `no_speech_prob`: Non-speech probability
- `language`: Recognized language
- Calling the `save_to_json()` method will save the above content to the specified `save_path`. If specified as a directory, the saved path will be `save_path/{your_audio_basename}.json`; if specified as a file, it will be saved directly to that file. Since JSON files do not support saving numpy arrays, the `numpy.array` types will be converted to lists.
* Additionally, it also supports obtaining visualized images and prediction results through attributes, as follows:
Multilingual Service Call Examples
Python
import base64
import requests
API_URL = "http://localhost:8080/video-classification" # Service URL
video_path = "./demo.mp4"
output_video_path = "./out.mp4"
# Encode local video to Base64
with open(video_path, "rb") as file:
video_bytes = file.read()
video_data = base64.b64encode(video_bytes).decode("ascii")
payload = {"video": video_data} # Base64 encoded file content or video URL
# Call API
response = requests.post(API_URL, json=payload)
# Process API response
assert response.status_code == 200
result = response.json()["result"]
with open(output_video_path, "wb") as file:
file.write(base64.b64decode(result["video"]))
print(f"Output video saved at {output_video_path}")
print("\nCategories:")
print(result["categories"])
C++
#include <iostream>
#include "cpp-httplib/httplib.h" // https://github.com/Huiyicc/cpp-httplib
#include "nlohmann/json.hpp" // https://github.com/nlohmann/json
#include "base64.hpp" // https://github.com/tobiaslocker/base64
int main() {
httplib::Client client("localhost:8080");
const std::string videoPath = "./demo.mp4";
const std::string outputImagePath = "./out.mp4";
httplib::Headers headers = {
{"Content-Type", "application/json"}
};
// Encode local video to Base64
std::ifstream file(videoPath, std::ios::binary | std::ios::ate);
std::streamsize size = file.tellg();
file.seekg(0, std::ios::beg);
std::vector<char> buffer(size);
if (!file.read(buffer.data(), size)) {
std::cerr << "Error reading file." << std::endl;
return 1;
}
std::string bufferStr(reinterpret_cast<const char*>(buffer.data()), buffer.size());
std::string encodedImage = base64::to_base64(bufferStr);
nlohmann::json jsonObj;
jsonObj["video"] = encodedImage;
std::string body = jsonObj.dump();
// Call API
auto response = client.Post("/video-classification", headers, body, "application/json");
// Process API response
if (response && response->status == 200) {
nlohmann::json jsonResponse = nlohmann::json::parse(response->body);
auto result = jsonResponse["result"];
encodedImage = result["video"];
std::string decodedString = base64::from_base64(encodedImage);
std::vector<unsigned char> decodedImage(decodedString.begin(), decodedString.end());
std::ofstream outputImage(outPutImagePath, std::ios::binary | std::ios::out);
if (outputImage.is_open()) {
outputImage.write(reinterpret_cast<char*>(decodedImage.data()), decodedImage.size());
outputImage.close();
std::cout << "Output video saved at " << outPutImagePath << std::endl;
} else {
std::cerr << "Unable to open file for writing: " << outPutImagePath << std::endl;
}
auto categories = result["categories"];
std::cout << "\nCategories:" << std::endl;
for (const auto& category : categories) {
std::cout << category << std::endl;
}
} else {
std::cout << "Failed to send HTTP request." << std::endl;
return 1;
}
return 0;
}
Java
import okhttp3.*;
import com.fasterxml.jackson.databind.ObjectMapper;
import com.fasterxml.jackson.databind.JsonNode;
import com.fasterxml.jackson.databind.node.ObjectNode;
import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
import java.util.Base64;
public class Main {
public static void main(String[] args) throws IOException {
String API_URL = "http://localhost:8080/video-classification"; // Service URL
String videoPath = "./demo.mp4"; // Local video
String outputImagePath = "./out.mp4"; // Output video
// Encode local video to Base64
File file = new File(videoPath);
byte[] fileContent = java.nio.file.Files.readAllBytes(file.toPath());
String videoData = Base64.getEncoder().encodeToString(fileContent);
ObjectMapper objectMapper = new ObjectMapper();
ObjectNode params = objectMapper.createObjectNode();
params.put("video", videoData); // Base64 encoded file content or video URL
// Create OkHttpClient instance
OkHttpClient client = new OkHttpClient();
MediaType JSON = MediaType.Companion.get("application/json; charset=utf-8");
RequestBody body = RequestBody.Companion.create(params.toString(), JSON);
Request request = new Request.Builder()
.url(API_URL)
.post(body)
.build();
// Call API and process API response
try (Response response = client.newCall(request).execute()) {
if (response.isSuccessful()) {
String responseBody = response.body().string();
JsonNode resultNode = objectMapper.readTree(responseBody);
JsonNode result = resultNode.get("result");
String base64Image = result.get("video").asText();
JsonNode categories = result.get("categories");
byte[] videoBytes = Base64.getDecoder().decode(base64Image);
try (FileOutputStream fos = new FileOutputStream(outputImagePath)) {
fos.write(videoBytes);
}
System.out.println("Output video saved at " + outputImagePath);
System.out.println("\nCategories: " + categories.toString());
} else {
System.err.println("Request failed with code: " + response.code());
}
}
}
}
Go
package main
import (
"bytes"
"encoding/base64"
"encoding/json"
"fmt"
"io/ioutil"
"net/http"
)
func main() {
API_URL := "http://localhost:8080/video-classification"
videoPath := "./demo.mp4"
outputImagePath := "./out.mp4"
// Base64 encode the local video
videoBytes, err := ioutil.ReadFile(videoPath)
if err != nil {
fmt.Println("Error reading video file:", err)
return
}
videoData := base64.StdEncoding.EncodeToString(videoBytes)
payload := map[string]string{"video": videoData} // Base64 encoded file content or video URL
payloadBytes, err := json.Marshal(payload)
if err != nil {
fmt.Println("Error marshaling payload:", err)
return
}
// Call the API
client := &http.Client{}
req, err := http.NewRequest("POST", API_URL, bytes.NewBuffer(payloadBytes))
if err != nil {
fmt.Println("Error creating request:", err)
return
}
res, err := client.Do(req)
if err != nil {
fmt.Println("Error sending request:", err)
return
}
defer res.Body.Close()
// Handle the API response
body, err := ioutil.ReadAll(res.Body)
if err != nil {
fmt.Println("Error reading response body:", err)
return
}
type Response struct {
Result struct {
Image string `json:"video"`
Categories []map[string]interface{} `json:"categories"`
} `json:"result"`
}
var respData Response
err = json.Unmarshal([]byte(string(body)), &respData)
if err != nil {
fmt.Println("Error unmarshaling response body:", err)
return
}
outputImageData, err := base64.StdEncoding.DecodeString(respData.Result.Image)
if err != nil {
fmt.Println("Error decoding base64 video data:", err)
return
}
err = ioutil.WriteFile(outputImagePath, outputImageData, 0644)
if err != nil {
fmt.Println("Error writing video to file:", err)
return
}
fmt.Printf("Image saved at %s.mp4\n", outputImagePath)
fmt.Println("\nCategories:")
for _, category := range respData.Result.Categories {
fmt.Println(category)
}
}
C#
using System;
using System.IO;
using System.Net.Http;
using System.Net.Http.Headers;
using System.Text;
using System.Threading.Tasks;
using Newtonsoft.Json.Linq;
class Program
{
static readonly string API_URL = "http://localhost:8080/video-classification";
static readonly string videoPath = "./demo.mp4";
static readonly string outputImagePath = "./out.mp4";
static async Task Main(string[] args)
{
var httpClient = new HttpClient();
// Base64 encode the local video
byte[] videoBytes = File.ReadAllBytes(videoPath);
string video_data = Convert.ToBase64String(videoBytes);
var payload = new JObject{ { "video", video_data } }; // Base64 encoded file content or video URL
var content = new StringContent(payload.ToString(), Encoding.UTF8, "application/json");
// Call the API
HttpResponseMessage response = await httpClient.PostAsync(API_URL, content);
response.EnsureSuccessStatusCode();
// Handle the API response
string responseBody = await response.Content.ReadAsStringAsync();
JObject jsonResponse = JObject.Parse(responseBody);
string base64Image = jsonResponse["result"]["video"].ToString();
byte[] outputImageBytes = Convert.FromBase64String(base64Image);
File.WriteAllBytes(outputImagePath, outputImageBytes);
Console.WriteLine($"Output video saved at {outputImagePath}");
Console.WriteLine("\nCategories:");
Console.WriteLine(jsonResponse["result"]["categories"].ToString());
}
}
Node.js
const axios = require('axios');
const fs = require('fs');
const API_URL = 'http://localhost:8080/video-classification'
const videoPath = './demo.mp4'
const outputImagePath = "./out.mp4";
let config = {
method: 'POST',
maxBodyLength: Infinity,
url: API_URL,
data: JSON.stringify({
'video': encodeImageToBase64(videoPath) // Base64 encoded file content or video URL
})
};
// Base64 encode the local video
function encodeImageToBase64(filePath) {
const bitmap = fs.readFileSync(filePath);
return Buffer.from(bitmap).toString('base64');
}
// Call the API
axios.request(config)
.then((response) => {
// Process the API response
const result = response.data["result"];
const videoBuffer = Buffer.from(result["video"], 'base64');
fs.writeFile(outputImagePath, videoBuffer, (err) => {
if (err) throw err;
console.log(`Output video saved at ${outputImagePath}`);
});
console.log("\nCategories:");
console.log(result["categories"]);
})
.catch((error) => {
console.log(error);
});
PHP
<?php
$API_URL = "http://localhost:8080/video-classification"; // Service URL
$video_path = "./demo.mp4";
$output_video_path = "./out.mp4";
// Base64 encode the local video
$video_data = base64_encode(file_get_contents($video_path));
$payload = array("video" => $video_data); // Base64 encoded file content or video URL
// Call the API
$ch = curl_init($API_URL);
curl_setopt($ch, CURLOPT_POST, true);
curl_setopt($ch, CURLOPT_POSTFIELDS, json_encode($payload));
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
$response = curl_exec($ch);
curl_close($ch);
// Process the API response
$result = json_decode($response, true)["result"];
file_put_contents($output_video_path, base64_decode($result["video"]));
echo "Output video saved at " . $output_video_path . "\n";
echo "\nCategories:\n";
print_r($result["categories"]);
?>