Alibaba Cloud Model Studio:SDK Java de reconhecimento de fala gravada Paraformer

import com.alibaba.dashscope.audio.asr.transcription.*;
import com.google.gson.*;

import java.util.Arrays;

public class Main {
    public static void main(String[] args) {
        // The following configuration is for the China (Beijing) region. Replace "{WorkspaceId}" with your actual workspace ID. The configuration varies by region.
        Constants.baseHttpApiUrl = "https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1";
        // Create transcription request parameters
        TranscriptionParam param =
                TranscriptionParam.builder()
                        // If the API Key is not configured in an environment variable, replace apiKey with your own API Key
                        //.apiKey("apikey")
                        .model("paraformer-v2")
                        // "language_hints" is only supported by the paraformer-v2 model
                        .parameter("language_hints", new String[]{"zh", "en"})
                        .fileUrls(
                                Arrays.asList(
                                        "https://dashscope.oss-cn-beijing.aliyuncs.com/samples/audio/paraformer/hello_world_female2.wav"))
                        .build();
        try {
            Transcription transcription = new Transcription();
            // Submit transcription request
            TranscriptionResult result = transcription.asyncCall(param);
            System.out.println("RequestId: " + result.getRequestId());
            // Block and wait for the task to complete and get the result
            result = transcription.wait(
                    TranscriptionQueryParam.FromTranscriptionParam(param, result.getTaskId()));
            // Print result
            System.out.println(result.getOutput());
        } catch (Exception e) {
            System.out.println("error: " + e);
        }
        System.exit(0);
    }
}

import com.alibaba.dashscope.audio.asr.transcription.*;
import com.alibaba.dashscope.common.TaskStatus;
import com.google.gson.*;

import java.util.Arrays;

public class Main {
    public static void main(String[] args) {
        // The following configuration is for the China (Beijing) region. Replace "{WorkspaceId}" with your actual workspace ID. The configuration varies by region.
        Constants.baseHttpApiUrl = "https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1";
        // Create transcription request parameters
        TranscriptionParam param =
                TranscriptionParam.builder()
                        // If the API Key is not configured in an environment variable, replace apiKey with your own API Key
                        //.apiKey("apikey")
                        .model("paraformer-v2")
                        // "language_hints" is only supported by the paraformer-v2 model
                        .parameter("language_hints", new String[]{"zh", "en"})
                        .fileUrls(
                                Arrays.asList(
                                        "https://dashscope.oss-cn-beijing.aliyuncs.com/samples/audio/paraformer/hello_world_female2.wav"))
                        .build();
        try {
            Transcription transcription = new Transcription();
            // Submit transcription request
            TranscriptionResult result = transcription.asyncCall(param);
            System.out.println("RequestId: " + result.getRequestId());
            // Loop to get the task result until the task finishes
            while (true) {
                result = transcription.fetch(TranscriptionQueryParam.FromTranscriptionParam(param, result.getTaskId()));
                if (result.getTaskStatus() == TaskStatus.SUCCEEDED || result.getTaskStatus() == TaskStatus.FAILED) {
                    break;
                }
                Thread.sleep(1000);
            }
            // Print result
            System.out.println(result.getOutput());
        } catch (Exception e) {
            System.out.println("error: " + e);
        }
        System.exit(0);
    }
}

TranscriptionParam param = TranscriptionParam.builder()
  .model("paraformer-v2")
  // "language_hints" is only supported by the paraformer-v2 model
  .parameter("language_hints", new String[]{"zh", "en"})
  .fileUrls(
          Arrays.asList(
                  "https://dashscope.oss-cn-beijing.aliyuncs.com/samples/audio/paraformer/hello_world_female2.wav"))
  .build();

{
    "file_url":"https://dashscope.oss-cn-beijing.aliyuncs.com/samples/audio/paraformer/hello_world_female2.wav",
    "properties":{
        "audio_format":"pcm_s16le",
        "channels":[
            0
        ],
        "original_sampling_rate":16000,
        "original_duration_in_milliseconds":3834
    },
    "transcripts":[
        {
            "channel_id":0,
            "content_duration_in_milliseconds":3720,
            "text":"Hello world, this is the Alibaba speech laboratory.",
            "sentences":[
                {
                    "begin_time":100,
                    "end_time":3820,
                    "text":"Hello world, this is the Alibaba speech laboratory.",
                    "sentence_id":1,
                    "speaker_id":0, //This field is only displayed when automatic speaker diarization is enabled
                    "words":[
                        {
                            "begin_time":100,
                            "end_time":596,
                            "text":"Hello ",
                            "punctuation":""
                        },
                        {
                            "begin_time":596,
                            "end_time":844,
                            "text":"world",
                            "punctuation":", "
                        }
                        // Other content omitted here
                    ]
                }
            ]
        }
    ]
}

// Create transcription request parameters
TranscriptionParam param =
        TranscriptionParam.builder()
                // If the API Key is not configured in an environment variable, replace apiKey with your own API Key
                //.apiKey("apikey")
                .model("paraformer-v2")
                // "language_hints" is only supported by the paraformer-v2 model
                .parameter("language_hints", new String[]{"zh", "en"})
                .fileUrls(
                        Arrays.asList(
                                "https://dashscope.oss-cn-beijing.aliyuncs.com/samples/audio/paraformer/hello_world_female2.wav"))
                .build();
try {
    Transcription transcription = new Transcription();
    // Submit transcription request
    TranscriptionResult result = transcription.asyncCall(param);
    System.out.println("RequestId: " + result.getRequestId());
    TranscriptionQueryParam queryParam = TranscriptionQueryParam.FromTranscriptionParam(param, result.getTaskId());

} catch (Exception e) {
    System.out.println("error: " + e);
}

Por exemplo:

• Object Storage Service (recomendado):

  • Use o serviço de armazenamento de objetos de um provedor de nuvem (como o Alibaba Cloud OSS) para fazer upload de arquivos de áudio para um bucket e configurá-los para acesso público.
  • Vantagens: Alta disponibilidade, suporte a aceleração CDN, gerenciamento fácil.

• Servidor web:

  • Coloque arquivos de áudio em um servidor web que suporte acesso HTTP/HTTPS (como Nginx ou Apache).
  • Vantagens: Adequado para pequenos projetos ou testes locais.

• Content Delivery Network (CDN):

  • Hospede arquivos de áudio em uma CDN e acesse-os pela URL fornecida pela CDN.
  • Vantagens: Entrega acelerada de arquivos, adequada para cenários de alta concorrência.

Faça upload dos arquivos de áudio com base no método de armazenamento/hospedagem escolhido, por exemplo:

• Object Storage Service:

  • Faça login no console do provedor de nuvem e crie um bucket.
  • Faça upload dos arquivos de áudio e defina as permissões do arquivo como "leitura pública" ou gere links de acesso temporário.

• Servidor web:

  • Coloque os arquivos de áudio no diretório designado do servidor (como /var/www/html/audio/).
  • Garanta que os arquivos sejam acessíveis via HTTP/HTTPS.

Por exemplo:

• Object Storage Service:

  • Após o upload, o sistema gera automaticamente uma URL de acesso público (geralmente no formato https://<bucket-name>.<region>.aliyuncs.com/<file-name>).
  • Se precisar de um domínio mais amigável, vincule um domínio personalizado e ative HTTPS.

• Servidor web:

  • A URL de acesso ao arquivo é tipicamente o endereço do servidor mais o caminho do arquivo (como https://your-domain.com/audio/file.mp3).

• CDN:

  • Após configurar a aceleração CDN, use a URL fornecida pela CDN (como https://cdn.your-domain.com/audio/file.mp3).

Em um ambiente de rede pública, garanta que a URL gerada seja acessível, por exemplo:

• Abra a URL em um navegador e verifique se o arquivo de áudio pode ser reproduzido.
• Use ferramentas (como curl ou Postman) para verificar se a URL retorna uma resposta HTTP correta (código de status 200).