Audio

Make predictions on audio inputs

---

To make predictions on audio inputs, you need to use a workflow. Workflows is a useful Clarifai's feature that allows you to combine multiple models and carry out different operations. You can use Clarifai's built-in models or your own custom models.

In this case, we'll create a workflow that first does audio-to-text transcription and then makes predictions from the transcribed texts.

The file size of each audio input should be less than 20MB.

info

The initialization code used in the following examples is outlined in detail on the client installation page.

Create a Workflow

In this example, we'll create a simple workflow that first converts an audio file to text and then analyses the sentiment of the transcribed text.

We'll connect the following two models to achieve our objective:

• The asr-wav2vec2-base-960h-english, which converts English audio to English text.
• The sentiment-analysis-distilbert-english, which predicts whether the sentiment of an English text is positive or negative.

We'll specify the IDs of the models and their versions—since a model can have several versions.

Python

########################################################################################
# In this section, we set the user authentication, app ID, and the details of the new
# custom workflow we want to create. Change these strings to run your own example.
########################################################################################

USER_ID = 'YOUR_USER_ID_HERE'
# Your PAT (Personal Access Token) can be found in the portal under Authentification
PAT = 'YOUR_PAT_HERE'
APP_ID = 'YOUR_APP_ID_HERE'
# Change these to create your own custom workflow
WORKFLOW_ID = 'my-custom-workflow'
NODE_ID_1 = 'audio-to-text'
MODEL_ID_1 = 'asr-wav2vec2-base-960h-english'
MODEL_VERSION_ID_1 = 'f4deae70a473492a8e2f9b7bb1dbee85'

NODE_ID_2 = 'sentiment-analysis'
MODEL_ID_2 = 'sentiment-analysis-distilbert-english'
MODEL_VERSION_ID_2 = 'c0b09e606db94d9bae7eb40c626192fc'

##########################################################################
# YOU DO NOT NEED TO CHANGE ANYTHING BELOW THIS LINE TO RUN THIS EXAMPLE
##########################################################################

from clarifai_grpc.channel.clarifai_channel import ClarifaiChannel
from clarifai_grpc.grpc.api import resources_pb2, service_pb2, service_pb2_grpc
from clarifai_grpc.grpc.api.status import status_code_pb2

channel = ClarifaiChannel.get_grpc_channel()
stub = service_pb2_grpc.V2Stub(channel)

metadata = (('authorization', 'Key ' + PAT),)

userDataObject = resources_pb2.UserAppIDSet(user_id=USER_ID, app_id=APP_ID) # The userDataObject is required when using a PAT

post_workflows_response = stub.PostWorkflows(
    service_pb2.PostWorkflowsRequest(
      user_app_id=userDataObject,  
      workflows=[
        resources_pb2.Workflow(
          id=WORKFLOW_ID,
          nodes=[
            resources_pb2.WorkflowNode(
              id=NODE_ID_1,
              model=resources_pb2.Model(
                id=MODEL_ID_1,
                model_version=resources_pb2.ModelVersion(
                  id=MODEL_VERSION_ID_1
                )
              )
            ),
            resources_pb2.WorkflowNode(
              id=NODE_ID_2,
              model=resources_pb2.Model(
                id=MODEL_ID_2,
                model_version=resources_pb2.ModelVersion(
                  id=MODEL_VERSION_ID_2
                )
              ),
              node_inputs=[
                resources_pb2.NodeInput(node_id=NODE_ID_1)
                ]
            ),
          ]
        )
      ]
    ),
    metadata=metadata
)               

if post_workflows_response.status.code != status_code_pb2.SUCCESS:
    print(post_workflows_response.status)
    raise Exception("Post workflows failed, status: " + post_workflows_response.status.description) 

JavaScript (REST)

<!--index.html file-->

<script>
    //////////////////////////////////////////////////////////////////////////////////////////
    // In this section, we set the user authentication, app ID, and the details of the new
    // custom workflow we want to create. Change these strings to run your own example.
    /////////////////////////////////////////////////////////////////////////////////////////

    const USER_ID = 'YOUR_USER_ID_HERE';
    // Your PAT (Personal Access Token) can be found in the portal under Authentification
    const PAT = 'YOUR_PAT_HERE';
    const APP_ID = 'YOUR_APP_ID_HERE';
    // Change these to create your own custom workflow
    const WORKFLOW_ID = 'my-custom-workflow';
    const NODE_ID_1 = 'audio-to-text';
    const MODEL_ID_1 = 'asr-wav2vec2-base-960h-english';
    const MODEL_VERSION_ID_1 = 'f4deae70a473492a8e2f9b7bb1dbee85';

    const NODE_ID_2 = 'sentiment-analysis';
    const MODEL_ID_2 = 'sentiment-analysis-distilbert-english';
    const MODEL_VERSION_ID_2 = 'c0b09e606db94d9bae7eb40c626192fc';

    ///////////////////////////////////////////////////////////////////////////////////
    // YOU DO NOT NEED TO CHANGE ANYTHING BELOW THIS LINE TO RUN THIS EXAMPLE
    ///////////////////////////////////////////////////////////////////////////////////   

    const raw = JSON.stringify({
        "user_app_id": {
            "user_id": USER_ID,
            "app_id": APP_ID
        },
        "workflows": [{
            "id": WORKFLOW_ID,
            "nodes": [
                {
                    "id": NODE_ID_1,
                    "model": {
                        "id": MODEL_ID_1,
                        "model_version": {
                            "id": MODEL_VERSION_ID_1
                        }
                    }
                },
                {
                    "id": NODE_ID_2,
                    "model": {
                        "id": MODEL_ID_2,
                        "model_version": {
                            "id": MODEL_VERSION_ID_2
                        }
                    },
                        "node_inputs": [
                            {
                                "node_id": NODE_ID_1
                            }
                        ]
                }
            ]
        }]
    });

    const requestOptions = {
        method: 'POST',
        headers: {
            'Accept': 'application/json',
            'Authorization': 'Key ' + PAT
        },
        body: raw
    };

    fetch(`https://api.clarifai.com/v2/workflows`, requestOptions)
        .then(response => response.text())
        .then(result => console.log(result))
        .catch(error => console.log('error', error));

</script>

NodeJS

//index.js file

//////////////////////////////////////////////////////////////////////////////////////////
// In this section, we set the user authentication, app ID, and the details of the new
// custom workflow we want to create. Change these strings to run your own example.
/////////////////////////////////////////////////////////////////////////////////////////

const USER_ID = 'YOUR_USER_ID_HERE';
// Your PAT (Personal Access Token) can be found in the portal under Authentification
const PAT = 'YOUR_PAT_HERE';
const APP_ID = 'YOUR_APP_ID_HERE';
// Change these to create your own custom workflow
const WORKFLOW_ID = 'my-custom-workflow';
const NODE_ID_1 = 'audio-to-text';
const MODEL_ID_1 = 'asr-wav2vec2-base-960h-english';
const MODEL_VERSION_ID_1 = 'f4deae70a473492a8e2f9b7bb1dbee85';

const NODE_ID_2 = 'sentiment-analysis';
const MODEL_ID_2 = 'sentiment-analysis-distilbert-english';
const MODEL_VERSION_ID_2 = 'c0b09e606db94d9bae7eb40c626192fc';

/////////////////////////////////////////////////////////////////////////////
// YOU DO NOT NEED TO CHANGE ANYTHING BELOW THIS LINE TO RUN THIS EXAMPLE
/////////////////////////////////////////////////////////////////////////////

const { ClarifaiStub, grpc } = require("clarifai-nodejs-grpc");

const stub = ClarifaiStub.grpc();

// This will be used by every Clarifai endpoint call
const metadata = new grpc.Metadata();
metadata.set("authorization", "Key " + PAT);

stub.PostWorkflows(
    {
        user_app_id: {
            "user_id": USER_ID,
            "app_id": APP_ID
        },
        workflows: [
            {
                id: WORKFLOW_ID,
                nodes: [
                    {
                        id: NODE_ID_1,
                        model: {
                            id: MODEL_ID_1,
                            model_version: {
                                id: MODEL_VERSION_ID_1
                            }
                        }
                    },
                    {
                        id: NODE_ID_2,
                        model: {
                            id: MODEL_ID_2,
                            model_version: {
                                id: MODEL_VERSION_ID_2
                            }
                        },
                        node_inputs: [
                            {
                                node_id: NODE_ID_1 
                            }
                        ]
                    }
                ]
            }
        ]
    },
    metadata,
    (err, response) => {
        if (err) {
            throw new Error(err);
        }

        if (response.status.code !== 10000) {
            throw new Error("Post workflows failed, status: " + response.status.description);
        }
    }
);

Java

package com.clarifai.example;

import com.clarifai.channel.ClarifaiChannel;
import com.clarifai.credentials.ClarifaiCallCredentials;
import com.clarifai.grpc.api.*;
import com.clarifai.grpc.api.status.StatusCode;

public class ClarifaiExample {

    //////////////////////////////////////////////////////////////////////////////////////////
    // In this section, we set the user authentication, app ID, and the details of the new
    // custom workflow we want to create. Change these strings to run your own example.
    /////////////////////////////////////////////////////////////////////////////////////////

    static final String USER_ID = "YOUR_USER_ID_HERE";
    //Your PAT (Personal Access Token) can be found in the portal under Authentication
    static final String PAT = "YOUR_PAT_HERE";
    static final String APP_ID = "YOUR_APP_ID_HERE";
    // Change these to create your own custom workflow
    static final String WORKFLOW_ID = "my-custom-workflow";
    static final String NODE_ID_1 = "audio-to-text";
    static final String MODEL_ID_1 = "asr-wav2vec2-base-960h-english";
    static final String MODEL_VERSION_ID_1 = "f4deae70a473492a8e2f9b7bb1dbee85";

    static final String NODE_ID_2 = "sentiment-analysis";
    static final String MODEL_ID_2 = "sentiment-analysis-distilbert-english";
    static final String MODEL_VERSION_ID_2 = "c0b09e606db94d9bae7eb40c626192fc";

    ///////////////////////////////////////////////////////////////////////////////////
    // YOU DO NOT NEED TO CHANGE ANYTHING BELOW THIS LINE TO RUN THIS EXAMPLE
    ///////////////////////////////////////////////////////////////////////////////////

    public static void main(String[] args) {

        V2Grpc.V2BlockingStub stub = V2Grpc.newBlockingStub(ClarifaiChannel.INSTANCE.getGrpcChannel())
            .withCallCredentials(new ClarifaiCallCredentials(PAT));

        MultiWorkflowResponse postWorkflowsResponse = stub.postWorkflows(
            PostWorkflowsRequest.newBuilder()
            .setUserAppId(UserAppIDSet.newBuilder().setUserId(USER_ID).setAppId(APP_ID))
            .addWorkflows(
                Workflow.newBuilder()
                .setId(WORKFLOW_ID)
                .addNodes(
                    WorkflowNode.newBuilder()
                    .setId(NODE_ID_1)
                    .setModel(
                        Model.newBuilder()
                        .setId(MODEL_ID_1)
                        .setModelVersion(ModelVersion.newBuilder().setId(MODEL_VERSION_ID_1))
                    )
                )
                .addNodes(
                    WorkflowNode.newBuilder()
                    .setId(NODE_ID_2)
                    .setModel(
                        Model.newBuilder()
                        .setId(MODEL_ID_2)
                        .setModelVersion(ModelVersion.newBuilder().setId(MODEL_VERSION_ID_2))
                    )
                    .addNodeInputs(NodeInput.newBuilder().setNodeId(NODE_ID_1))
                )
            ).build()
        );

        if (postWorkflowsResponse.getStatus().getCode() != StatusCode.SUCCESS) {
            throw new RuntimeException("Post workflows failed, status: " + postWorkflowsResponse.getStatus());
        }

    }

}

cURL

curl -X POST "https://api.clarifai.com/v2/users/YOUR_USER_ID_HERE/apps/YOUR_APP_ID_HERE/workflows" \
    -H "Content-Type: application/json" \
    -H "Authorization: Key YOUR_PAT_HERE" \
    --data-raw '{
      "workflows": [{
        "id": "my-custom-workflow",
        "nodes": [
          {
            "id": "audio-to-text",
            "model": {
              "id": "asr-wav2vec2-base-960h-english",
              "model_version": {
                "id": "f4deae70a473492a8e2f9b7bb1dbee85"
              }
            }
          },
          {
            "id": "sentiment-analysis",
            "model": {
              "id": "sentiment-analysis-distilbert-english",
              "model_version": {
                "id": "c0b09e606db94d9bae7eb40c626192fc"
              }
            },
              "node_inputs": [
                {
                  "node_id": "audio-to-text"
                }
              ]
          }
        ]
      }]
    }'

Predict via URL

After creating the workflow, let's now use it to convert this audio file to text and then get the sentiment of the generated text.

The response will contain the predictions each model in the workflow returns for the audio input.

Python

#############################################################################
# In this section, we set the user authentication, app ID, workflow ID, and  
# audio URL. Change these strings to run your own example.
##############################################################################

USER_ID = 'YOUR_USER_ID_HERE'
# Your PAT (Personal Access Token) can be found in the portal under Authentification
PAT = 'YOUR_PAT_HERE'
APP_ID = 'YOUR_APP_ID_HERE'
# Change these to make your own predictions
WORKFLOW_ID = 'my-custom-workflow'
AUDIO_URL = 'https://samples.clarifai.com/negative_sentence_1.wav'

##########################################################################
# YOU DO NOT NEED TO CHANGE ANYTHING BELOW THIS LINE TO RUN THIS EXAMPLE
##########################################################################

from clarifai_grpc.channel.clarifai_channel import ClarifaiChannel
from clarifai_grpc.grpc.api import resources_pb2, service_pb2, service_pb2_grpc
from clarifai_grpc.grpc.api.status import status_code_pb2

channel = ClarifaiChannel.get_grpc_channel()
stub = service_pb2_grpc.V2Stub(channel)

metadata = (('authorization', 'Key ' + PAT),)

userDataObject = resources_pb2.UserAppIDSet(user_id=USER_ID, app_id=APP_ID) # The userDataObject is required when using a PAT

post_workflow_results_response = stub.PostWorkflowResults(
    service_pb2.PostWorkflowResultsRequest(
        user_app_id=userDataObject,  
        workflow_id=WORKFLOW_ID,
        inputs=[
            resources_pb2.Input(
                data=resources_pb2.Data(
                    audio=resources_pb2.Audio(
                        url=AUDIO_URL
                    )
                )
            )
        ]
    ),
    metadata=metadata
)
if post_workflow_results_response.status.code != status_code_pb2.SUCCESS:
    print(post_workflow_results_response.status)
    raise Exception("Post workflow results failed, status: " + post_workflow_results_response.status.description)

# We'll get one WorkflowResult for each input we used above. Because of one input, we have here one WorkflowResult
results = post_workflow_results_response.results[0]

# Each model we have in the workflow will produce its output
for output in results.outputs:    
    model = output.model    
    print("Output for the model: `%s`" % model.id)   
    for concept in output.data.concepts:        
        print("\t%s %.2f" % (concept.name, concept.value)) 
    print(output.data.text.raw)     

# Uncomment this line to print the full Response JSON
#print(results) 

JavaScript (REST)

<!--index.html file-->

<script>
    ///////////////////////////////////////////////////////////////////////////////////
    // In this section, we set the user authentication, app ID, workflow ID, and
    // audio URL. Change these strings to run your own example.
    ///////////////////////////////////////////////////////////////////////////////////
  
    const USER_ID = "YOUR_USER_ID_HERE";
    // Your PAT (Personal Access Token) can be found in the portal under Authentification
    const PAT = "YOUR_PAT_HERE";
    const APP_ID = "YOUR_APP_ID_HERE";
    // Change these to make your own predictions
    const WORKFLOW_ID = "my-custom-workflow";
    const AUDIO_URL = "https://samples.clarifai.com/negative_sentence_1.wav";
  
    ///////////////////////////////////////////////////////////////////////////////////
    // YOU DO NOT NEED TO CHANGE ANYTHING BELOW THIS LINE TO RUN THIS EXAMPLE
    /////////////////////////////////////////////////////////////////////////////////// 
  
    const raw = JSON.stringify({
      "user_app_id": {
        "user_id": USER_ID,
        "app_id": APP_ID
      },
      "inputs": [
        {
          "data": {
            "audio": {
              "url": AUDIO_URL
            }
          }
        }
      ]
    });
  
    const requestOptions = {
      method: 'POST',
      headers: {
        'Accept': 'application/json',
        'Authorization': 'Key ' + PAT
      },
      body: raw
    };
  
    fetch(`https://api.clarifai.com/v2/workflows/${WORKFLOW_ID}/results`, requestOptions)
      .then(response => response.text())
      .then(result => console.log(result))
      .catch(error => console.log('error', error));
  </script>

NodeJS

//index.js file

///////////////////////////////////////////////////////////////////////////////////
// In this section, we set the user authentication, app ID, workflow ID, and
// audio URL. Change these strings to run your own example.
///////////////////////////////////////////////////////////////////////////////////

const USER_ID = 'YOUR_USER_ID_HERE';
// Your PAT (Personal Access Token) can be found in the portal under Authentification
const PAT = 'YOUR_PAT_HERE';
const APP_ID = 'YOUR_APP_ID_HERE';
// Change these to make your own predictions
const WORKFLOW_ID = "my-custom-workflow";
const AUDIO_URL = "https://samples.clarifai.com/negative_sentence_1.wav";

/////////////////////////////////////////////////////////////////////////////
// YOU DO NOT NEED TO CHANGE ANYTHING BELOW THIS LINE TO RUN THIS EXAMPLE
/////////////////////////////////////////////////////////////////////////////

const { ClarifaiStub, grpc } = require("clarifai-nodejs-grpc");

const stub = ClarifaiStub.grpc();

// This will be used by every Clarifai endpoint call
const metadata = new grpc.Metadata();
metadata.set("authorization", "Key " + PAT);

stub.PostWorkflowResults(
  {
    user_app_id: {
      "user_id": USER_ID,
      "app_id": APP_ID,
    },
    workflow_id: WORKFLOW_ID,
    inputs: [{ data: { audio: { url: AUDIO_URL } } }],
  },
  metadata,
  (err, response) => {
    if (err) {
      throw new Error(err);
    }

    if (response.status.code !== 10000) {
      throw new Error(
        "Post workflow results failed, status: " + response.status.description
      );
    }

    // We'll get one WorkflowResult for each input we used above. Because of one input, we have here 
    // one WorkflowResult
    const results = response.results[0];

    // Each model we have in the workflow will produce its output   
    for (const output of results.outputs) {
      const model = output.model;
      console.log("Output for the model: `" + model.id + "`");        
      for (const concept of output.data.concepts){    
        console.log("\t" + concept.name + " " + concept.value);        
      } 
      if(output.data.text){
      console.log(output.data.text.raw);        
      }               
    }
  }
);

Java

package com.clarifai.example;

import com.clarifai.channel.ClarifaiChannel;
import com.clarifai.credentials.ClarifaiCallCredentials;
import com.clarifai.grpc.api.*;
import com.clarifai.grpc.api.status.StatusCode;

public class ClarifaiExample {

    ///////////////////////////////////////////////////////////////////////////////////
    // In this section, we set the user authentication, app ID, workflow ID, and
    // audio URL. Change these strings to run your own example.
    ///////////////////////////////////////////////////////////////////////////////////

    static final String USER_ID = "YOUR_USER_ID_HERE";
    //Your PAT (Personal Access Token) can be found in the portal under Authentication
    static final String PAT = "YOUR_PAT_HERE";
    static final String APP_ID = "YOUR_APP_ID_HERE";
    // Change these to make your own predictions
    static final String WORKFLOW_ID = "my-custom-workflow";
    static final String AUDIO_URL = "https://samples.clarifai.com/negative_sentence_1.wav";

    ///////////////////////////////////////////////////////////////////////////////////
    // YOU DO NOT NEED TO CHANGE ANYTHING BELOW THIS LINE TO RUN THIS EXAMPLE
    ///////////////////////////////////////////////////////////////////////////////////

    public static void main(String[] args) {

        V2Grpc.V2BlockingStub stub = V2Grpc.newBlockingStub(ClarifaiChannel.INSTANCE.getGrpcChannel())
            .withCallCredentials(new ClarifaiCallCredentials(PAT));

        PostWorkflowResultsResponse postWorkflowResultsResponse = stub.postWorkflowResults(
            PostWorkflowResultsRequest.newBuilder()
            .setUserAppId(UserAppIDSet.newBuilder().setUserId(USER_ID).setAppId(APP_ID))
            .setWorkflowId(WORKFLOW_ID)
            .addInputs(
                Input.newBuilder().setData(
                    Data.newBuilder().setAudio(
                        Audio.newBuilder().setUrl(AUDIO_URL)
                    )
                )
            )
            .build()
        );

        if (postWorkflowResultsResponse.getStatus().getCode() != StatusCode.SUCCESS) {
            throw new RuntimeException("Post workflow results failed, status: " + postWorkflowResultsResponse.getStatus());
        }

        // We'll get one WorkflowResult for each input we used above. Because of one input, we have here
        // one WorkflowResult
        WorkflowResult results = postWorkflowResultsResponse.getResults(0);

        // Each model we have in the workflow will produce its output
        for (Output output: results.getOutputsList()) {
            Model model = output.getModel();
            System.out.println("Output for the model: `" + model.getId() + "`");   
            for (Concept concept: output.getData().getConceptsList()) {       
            	System.out.printf("\t%s %.2f%n",concept.getName(), concept.getValue());                 
            }
            System.out.println(output.getData().getText().getRaw());
        }

    }

}

cURL

curl -X POST "https://api.clarifai.com/v2/users/YOUR_USER_ID_HERE/apps/YOUR_APP_ID_HERE/workflows/YOUR_WORKFLOW_ID_HERE/results" \
  -H "authorization: Key YOUR_PAT_HERE" \
  -H "content-type: application/json" \
  -d '{
    "inputs": [
        {
          "data": {
            "audio": {
              "url": "https://samples.clarifai.com/negative_sentence_1.wav"
          }
        }
      }
    ]
}'

Code Output Example

Output for the model: `asr-wav2vec2-base-960h-english`
I AM NOT FLYING TO ENGLAND
Output for the model: `sentiment-analysis-distilbert-english`
	NEGATIVE 1.00
	POSITIVE 0.00

JSON Output Example

status {
  code: SUCCESS
  description: "Ok"
}
input {
  id: "9c39fec1ac9d4d58b7c1353c20cf8538"
  data {
    audio {
      url: "https://samples.clarifai.com/negative_sentence_1.wav"
    }
  }
}
outputs {
  id: "e04117c61f0b46fdb537b6663f235300"
  status {
    code: SUCCESS
    description: "Ok"
  }
  created_at {
    seconds: 1664555464
    nanos: 495787635
  }
  model {
    id: "asr-wav2vec2-base-960h-english"
    name: "facebook/wav2vec2-base-960h"
    created_at {
      seconds: 1634677145
      nanos: 661061000
    }
    app_id: "asr"
    output_info {
      output_config {
      }
      message: "Show output_info with: GET /models/{model_id}/output_info"
      fields_map {
        fields {
          key: "text"
          value {
            string_value: "text"
          }
        }
      }
    }
    model_version {
      id: "f4deae70a473492a8e2f9b7bb1dbee85"
      created_at {
        seconds: 1634677145
        nanos: 668993000
      }
      status {
        code: MODEL_TRAINED
        description: "Model is trained and ready"
      }
      visibility {
        gettable: PUBLIC
      }
      app_id: "asr"
      user_id: "facebook"
      metadata {
      }
      license: "Apache-2.0"
    }
    user_id: "facebook"
    input_info {
      fields_map {
        fields {
          key: "audio"
          value {
            string_value: "audio"
          }
        }
      }
    }
    train_info {
    }
    model_type_id: "audio-to-text"
    visibility {
      gettable: PUBLIC
    }
    modified_at {
      seconds: 1658884251
      nanos: 743015000
    }
    import_info {
    }
  }
  data {
    text {
      raw: "I AM NOT FLYING TO ENGLAND"
      text_info {
        encoding: "UnknownTextEnc"
      }
    }
  }
}
outputs {
  id: "2f37022e94e74ac7a7a5f5e927bbcf66"
  status {
    code: SUCCESS
    description: "Ok"
  }
  created_at {
    seconds: 1664555464
    nanos: 504551013
  }
  model {
    id: "sentiment-analysis-distilbert-english"
    name: "sentiment-analysis-distilbert-english"
    created_at {
      seconds: 1656524917
      nanos: 269700000
    }
    app_id: "text-classification"
    output_info {
      output_config {
      }
      message: "Show output_info with: GET /models/{model_id}/output_info"
      fields_map {
        fields {
          key: "concepts"
          value {
            string_value: "softmax"
          }
        }
      }
      params {
        fields {
          key: "max_concepts"
          value {
            number_value: 20.0
          }
        }
        fields {
          key: "min_value"
          value {
            number_value: 0.0
          }
        }
        fields {
          key: "select_concepts"
          value {
            list_value {
            }
          }
        }
      }
    }
    model_version {
      id: "c0b09e606db94d9bae7eb40c626192fc"
      created_at {
        seconds: 1656524917
        nanos: 276685000
      }
      status {
        code: MODEL_TRAINED
        description: "Model is trained and ready"
      }
      visibility {
        gettable: PUBLIC
      }
      app_id: "text-classification"
      user_id: "erfan"
      metadata {
        fields {
          key: "Model version logs zipped"
          value {
            string_value: "https://s3.amazonaws.com/clarifai-temp/prod/c0b09e606db94d9bae7eb40c626192fc.zip"
          }
        }
      }
    }
    user_id: "erfan"
    input_info {
      fields_map {
        fields {
          key: "text"
          value {
            string_value: "text"
          }
        }
      }
    }
    train_info {
      params {
        fields {
          key: "model_config"
          value {
            struct_value {
              fields {
                key: "_name_or_path"
                value {
                  string_value: "distilbert-base-uncased-finetuned-sst-2-english"
                }
              }
              fields {
                key: "activation"
                value {
                  string_value: "gelu"
                }
              }
              fields {
                key: "architectures"
                value {
                  list_value {
                    values {
                      string_value: "DistilBertForSequenceClassification"
                    }
                  }
                }
              }
              fields {
                key: "attention_dropout"
                value {
                  number_value: 0.1
                }
              }
              fields {
                key: "dim"
                value {
                  number_value: 768.0
                }
              }
              fields {
                key: "dropout"
                value {
                  number_value: 0.1
                }
              }
              fields {
                key: "finetuning_task"
                value {
                  string_value: "sst-2"
                }
              }
              fields {
                key: "hidden_dim"
                value {
                  number_value: 3072.0
                }
              }
              fields {
                key: "id2label"
                value {
                  struct_value {
                    fields {
                      key: "0"
                      value {
                        string_value: "NEGATIVE"
                      }
                    }
                    fields {
                      key: "1"
                      value {
                        string_value: "POSITIVE"
                      }
                    }
                  }
                }
              }
              fields {
                key: "initializer_range"
                value {
                  number_value: 0.02
                }
              }
              fields {
                key: "label2id"
                value {
                  struct_value {
                    fields {
                      key: "NEGATIVE"
                      value {
                        number_value: 0.0
                      }
                    }
                    fields {
                      key: "POSITIVE"
                      value {
                        number_value: 1.0
                      }
                    }
                  }
                }
              }
              fields {
                key: "max_position_embeddings"
                value {
                  number_value: 512.0
                }
              }
              fields {
                key: "model_type"
                value {
                  string_value: "distilbert"
                }
              }
              fields {
                key: "n_heads"
                value {
                  number_value: 12.0
                }
              }
              fields {
                key: "n_layers"
                value {
                  number_value: 6.0
                }
              }
              fields {
                key: "output_past"
                value {
                  bool_value: true
                }
              }
              fields {
                key: "pad_token_id"
                value {
                  number_value: 0.0
                }
              }
              fields {
                key: "qa_dropout"
                value {
                  number_value: 0.1
                }
              }
              fields {
                key: "seq_classif_dropout"
                value {
                  number_value: 0.2
                }
              }
              fields {
                key: "sinusoidal_pos_embds"
                value {
                  bool_value: false
                }
              }
              fields {
                key: "tie_weights_"
                value {
                  bool_value: true
                }
              }
              fields {
                key: "torch_dtype"
                value {
                  string_value: "float32"
                }
              }
              fields {
                key: "transformers_version"
                value {
                  string_value: "4.20.0"
                }
              }
              fields {
                key: "vocab_size"
                value {
                  number_value: 30522.0
                }
              }
            }
          }
        }
        fields {
          key: "tokenizer_config"
          value {
            struct_value {
              fields {
                key: "cls_token"
                value {
                  string_value: "[CLS]"
                }
              }
              fields {
                key: "do_basic_tokenize"
                value {
                  bool_value: true
                }
              }
              fields {
                key: "do_lower_case"
                value {
                  bool_value: true
                }
              }
              fields {
                key: "mask_token"
                value {
                  string_value: "[MASK]"
                }
              }
              fields {
                key: "model_max_length"
                value {
                  number_value: 512.0
                }
              }
              fields {
                key: "name_or_path"
                value {
                  string_value: "distilbert-base-uncased-finetuned-sst-2-english"
                }
              }
              fields {
                key: "never_split"
                value {
                  null_value: NULL_VALUE
                }
              }
              fields {
                key: "pad_token"
                value {
                  string_value: "[PAD]"
                }
              }
              fields {
                key: "sep_token"
                value {
                  string_value: "[SEP]"
                }
              }
              fields {
                key: "special_tokens_map_file"
                value {
                  null_value: NULL_VALUE
                }
              }
              fields {
                key: "strip_accents"
                value {
                  null_value: NULL_VALUE
                }
              }
              fields {
                key: "tokenize_chinese_chars"
                value {
                  bool_value: true
                }
              }
              fields {
                key: "tokenizer_class"
                value {
                  string_value: "DistilBertTokenizer"
                }
              }
              fields {
                key: "unk_token"
                value {
                  string_value: "[UNK]"
                }
              }
            }
          }
        }
      }
    }
    model_type_id: "text-classifier"
    visibility {
      gettable: PUBLIC
    }
    modified_at {
      seconds: 1656525047
      nanos: 842099000
    }
    import_info {
      params {
        fields {
          key: "model_name"
          value {
            string_value: "distilbert-base-uncased-finetuned-sst-2-english"
          }
        }
        fields {
          key: "pipeline_name"
          value {
            string_value: "text-classification"
          }
        }
        fields {
          key: "tokenizer_name"
          value {
            string_value: "distilbert-base-uncased-finetuned-sst-2-english"
          }
        }
        fields {
          key: "toolkit"
          value {
            string_value: "HuggingFace"
          }
        }
      }
    }
  }
  data {
    concepts {
      id: "NEGATIVE"
      name: "NEGATIVE"
      value: 0.9991872906684875
      app_id: "c4660162651d490285bcbfc5aff50bf0"
    }
    concepts {
      id: "POSITIVE"
      name: "POSITIVE"
      value: 0.0008126832544803619
      app_id: "c4660162651d490285bcbfc5aff50bf0"
    }
  }
}

Predict via Bytes

Below is an example of how you would send the bytes of an audio and receive predictions from the above-mentioned workflow.

Python

##############################################################################
# In this section, we set the user authentication, app ID, workflow ID, and  
# audio file location. Change these strings to run your own example.
##############################################################################

USER_ID = 'YOUR_USER_ID_HERE'
# Your PAT (Personal Access Token) can be found in the portal under Authentification
PAT = 'YOUR_PAT_HERE'
APP_ID = 'YOUR_APP_ID_HERE'
# Change these to make your own predictions
WORKFLOW_ID = 'my-custom-workflow'
AUDIO_FILE_LOCATION = 'YOUR_AUDIO_FILE_LOCATION_HERE' 

##########################################################################
# YOU DO NOT NEED TO CHANGE ANYTHING BELOW THIS LINE TO RUN THIS EXAMPLE
##########################################################################

from clarifai_grpc.channel.clarifai_channel import ClarifaiChannel
from clarifai_grpc.grpc.api import resources_pb2, service_pb2, service_pb2_grpc
from clarifai_grpc.grpc.api.status import status_code_pb2

channel = ClarifaiChannel.get_grpc_channel()
stub = service_pb2_grpc.V2Stub(channel)

metadata = (('authorization', 'Key ' + PAT),)

userDataObject = resources_pb2.UserAppIDSet(user_id=USER_ID, app_id=APP_ID) # The userDataObject is required when using a PAT

with open(AUDIO_FILE_LOCATION, "rb") as f:
    file_bytes = f.read()

post_workflow_results_response = stub.PostWorkflowResults(
    service_pb2.PostWorkflowResultsRequest(
        user_app_id=userDataObject,  
        workflow_id=WORKFLOW_ID,
        inputs=[
            resources_pb2.Input(
                data=resources_pb2.Data(
                    audio=resources_pb2.Audio(
                        base64=file_bytes
                    )
                )
            )
        ]
    ),
    metadata=metadata
)
if post_workflow_results_response.status.code != status_code_pb2.SUCCESS:
    print(post_workflow_results_response.status)
    raise Exception("Post workflow results failed, status: " + post_workflow_results_response.status.description)

# We'll get one WorkflowResult for each input we used above. Because of one input, we have here one WorkflowResult
results = post_workflow_results_response.results[0]

# Each model we have in the workflow will produce its output
for output in results.outputs:    
    model = output.model    
    print("Output for the model: `%s`" % model.id)   
    for concept in output.data.concepts:        
        print("\t%s %.2f" % (concept.name, concept.value)) 
    print(output.data.text.raw)     

# Uncomment this line to print the full Response JSON
#print(results) 

JavaScript (REST)

<!--index.html file-->

<script>
    //////////////////////////////////////////////////////////////////////////////////////////
    // In this section, we set the user authentication, app ID, workflow ID, and bytes of
    // the audio we want as an input. Change these strings to run your own example.
    /////////////////////////////////////////////////////////////////////////////////////////
  
    const USER_ID = "YOUR_USER_ID_HERE";
    // Your PAT (Personal Access Token) can be found in the portal under Authentification
    const PAT = "YOUR_PAT_HERE";
    const APP_ID = "YOUR_APP_ID_HERE";
    // Change these to make your own predictions
    const WORKFLOW_ID = "my-custom-workflow";
    const AUDIO_BYTES_STRING = "YOUR_BYTES_STRING_HERE";
  
    ///////////////////////////////////////////////////////////////////////////////////
    // YOU DO NOT NEED TO CHANGE ANYTHING BELOW THIS LINE TO RUN THIS EXAMPLE
    /////////////////////////////////////////////////////////////////////////////////// 
  
    const raw = JSON.stringify({
      "user_app_id": {
        "user_id": USER_ID,
        "app_id": APP_ID
      },
      "inputs": [
        {
          "data": {
            "audio": {
              "base64": AUDIO_BYTES_STRING
            }
          }
        }
      ]
    });
  
    const requestOptions = {
      method: 'POST',
      headers: {
        'Accept': 'application/json',
        'Authorization': 'Key ' + PAT
      },
      body: raw
    };
  
    fetch(`https://api.clarifai.com/v2/workflows/${WORKFLOW_ID}/results`, requestOptions)
      .then(response => response.text())
      .then(result => console.log(result))
      .catch(error => console.log('error', error));
  </script>

NodeJS

//index.js file

///////////////////////////////////////////////////////////////////////////////////
// In this section, we set the user authentication, app ID, workflow ID, and
// audio file location. Change these strings to run your own example.
///////////////////////////////////////////////////////////////////////////////////

const USER_ID = 'YOUR_USER_ID_HERE';
// Your PAT (Personal Access Token) can be found in the portal under Authentification
const PAT = 'YOUR_PAT_HERE';
const APP_ID = 'YOUR_APP_ID_HERE';
// Change these to make your own predictions
const WORKFLOW_ID = "my-custom-workflow";
const AUDIO_FILE_LOCATION = "YOUR_AUDIO_FILE_LOCATION_HERE";

/////////////////////////////////////////////////////////////////////////////
// YOU DO NOT NEED TO CHANGE ANYTHING BELOW THIS LINE TO RUN THIS EXAMPLE
/////////////////////////////////////////////////////////////////////////////

const { ClarifaiStub, grpc } = require("clarifai-nodejs-grpc");

const stub = ClarifaiStub.grpc();

// This will be used by every Clarifai endpoint call
const metadata = new grpc.Metadata();
metadata.set("authorization", "Key " + PAT);

const fs = require("fs");
const audioBytes = fs.readFileSync(AUDIO_FILE_LOCATION);

stub.PostWorkflowResults(
  {
    user_app_id: {
      "user_id": USER_ID,
      "app_id": APP_ID,
    },
    workflow_id: WORKFLOW_ID,
    inputs: [{ data: { audio: { base64: audioBytes } } }],
  },
  metadata,
  (err, response) => {
    if (err) {
      throw new Error(err);
    }

    if (response.status.code !== 10000) {
      throw new Error(
        "Post workflow results failed, status: " + response.status.description
      );
    }

    // We'll get one WorkflowResult for each input we used above. Because of one input, we have here 
    // one WorkflowResult
    const results = response.results[0];

    // Each model we have in the workflow will produce its output   
    for (const output of results.outputs) {
      const model = output.model;
      console.log("Output for the model: `" + model.id + "`");        
      for (const concept of output.data.concepts){    
        console.log("\t" + concept.name + " " + concept.value);        
      } 
      if(output.data.text){
      console.log(output.data.text.raw);        
      }               
    }
  }
);

Java

package com.clarifai.example;

import java.io.File;
import java.io.IOException;
import java.nio.file.Files;

import com.clarifai.channel.ClarifaiChannel;
import com.clarifai.credentials.ClarifaiCallCredentials;
import com.clarifai.grpc.api.*;
import com.clarifai.grpc.api.status.StatusCode;
import com.google.protobuf.ByteString;

public class ClarifaiExample {

    ///////////////////////////////////////////////////////////////////////////////////
    // In this section, we set the user authentication, app ID, workflow ID, and
    // audio file location. Change these strings to run your own example.
    ///////////////////////////////////////////////////////////////////////////////////

    static final String USER_ID = "YOUR_USER_ID_HERE";
    //Your PAT (Personal Access Token) can be found in the portal under Authentication
    static final String PAT = "YOUR_PAT_HERE";
    static final String APP_ID = "YOUR_APP_ID_HERE";
    // Change these to make your own predictions
    static final String WORKFLOW_ID = "my-custom-workflow";
    static final String AUDIO_FILE_LOCATION = "YOUR_AUDIO_FILE_LOCATION_HERE";

    ///////////////////////////////////////////////////////////////////////////////////
    // YOU DO NOT NEED TO CHANGE ANYTHING BELOW THIS LINE TO RUN THIS EXAMPLE
    ///////////////////////////////////////////////////////////////////////////////////

    public static void main(String[] args) throws IOException {

        V2Grpc.V2BlockingStub stub = V2Grpc.newBlockingStub(ClarifaiChannel.INSTANCE.getGrpcChannel())
            .withCallCredentials(new ClarifaiCallCredentials(PAT));

        PostWorkflowResultsResponse postWorkflowResultsResponse = stub.postWorkflowResults(
            PostWorkflowResultsRequest.newBuilder()
            .setUserAppId(UserAppIDSet.newBuilder().setUserId(USER_ID).setAppId(APP_ID))
            .setWorkflowId(WORKFLOW_ID)
            .addInputs(
                Input.newBuilder().setData(
                    Data.newBuilder().setAudio(
                        Audio.newBuilder().setBase64(ByteString.copyFrom(Files.readAllBytes(
                                new File(AUDIO_FILE_LOCATION).toPath()
                                )))
                    )
                )
            )
            .build()
        );

        if (postWorkflowResultsResponse.getStatus().getCode() != StatusCode.SUCCESS) {
            throw new RuntimeException("Post workflow results failed, status: " + postWorkflowResultsResponse.getStatus());
        }

        // We'll get one WorkflowResult for each input we used above. Because of one input, we have here
        // one WorkflowResult
        WorkflowResult results = postWorkflowResultsResponse.getResults(0);

        // Each model we have in the workflow will produce its output
        for (Output output: results.getOutputsList()) {
            Model model = output.getModel();
            System.out.println("Output for the model: `" + model.getId() + "`");   
            for (Concept concept: output.getData().getConceptsList()) {       
            	System.out.printf("\t%s %.2f%n",concept.getName(), concept.getValue());                 
            }
            System.out.println(output.getData().getText().getRaw());
        }

    }

}

cURL

curl -X POST "https://api.clarifai.com/v2/users/YOUR_USER_ID_HERE/apps/YOUR_APP_ID_HERE/workflows/YOUR_WORKFLOW_ID_HERE/results" \
  -H "authorization: Key YOUR_PAT_HERE" \
  -H "content-type: application/json" \
  -d '{
    "inputs": [
        {
          "data": {
            "audio": {
              "base64": "YOUR_BYTES_STRING_HERE"
          }
        }
      }
    ]
}'

Code Output Example

Output for the model: `asr-wav2vec2-base-960h-english`
I AM NOT FLYING TO ENGLAND
Output for the model: `sentiment-analysis-distilbert-english`
	NEGATIVE 1.00
	POSITIVE 0.00

JSON Output Example

status {
    code: SUCCESS
    description: "Ok"
  }
  input {
    id: "c4e45044f96a4fc9b1a4a1ddbd24ee26"
    data {
      audio {
        url: "https://samples.clarifai.com/placeholder.gif"
        base64: "true"
      }
    }
  }
  outputs {
    id: "557b489f3031436bbe5501f92d03461f"
    status {
      code: SUCCESS
      description: "Ok"
    }
    created_at {
      seconds: 1664805906
      nanos: 332458633
    }
    model {
      id: "asr-wav2vec2-base-960h-english"
      name: "facebook/wav2vec2-base-960h"
      created_at {
        seconds: 1634677145
        nanos: 661061000
      }
      app_id: "asr"
      output_info {
        output_config {
        }
        message: "Show output_info with: GET /models/{model_id}/output_info"
        fields_map {
          fields {
            key: "text"
            value {
              string_value: "text"
            }
          }
        }
      }
      model_version {
        id: "f4deae70a473492a8e2f9b7bb1dbee85"
        created_at {
          seconds: 1634677145
          nanos: 668993000
        }
        status {
          code: MODEL_TRAINED
          description: "Model is trained and ready"
        }
        visibility {
          gettable: PUBLIC
        }
        app_id: "asr"
        user_id: "facebook"
        metadata {
        }
        license: "Apache-2.0"
      }
      user_id: "facebook"
      input_info {
        fields_map {
          fields {
            key: "audio"
            value {
              string_value: "audio"
            }
          }
        }
      }
      train_info {
      }
      model_type_id: "audio-to-text"
      visibility {
        gettable: PUBLIC
      }
      modified_at {
        seconds: 1658884251
        nanos: 743015000
      }
      import_info {
      }
    }
    data {
      text {
        raw: "I AM NOT FLYING TO ENGLAND"
        text_info {
          encoding: "UnknownTextEnc"
        }
      }
    }
  }
  outputs {
    id: "e7d1bf12c487435bb005504dd402642e"
    status {
      code: SUCCESS
      description: "Ok"
    }
    created_at {
      seconds: 1664805906
      nanos: 336852253
    }
    model {
      id: "sentiment-analysis-distilbert-english"
      name: "sentiment-analysis-distilbert-english"
      created_at {
        seconds: 1656524917
        nanos: 269700000
      }
      app_id: "text-classification"
      output_info {
        output_config {
        }
        message: "Show output_info with: GET /models/{model_id}/output_info"
        fields_map {
          fields {
            key: "concepts"
            value {
              string_value: "softmax"
            }
          }
        }
        params {
          fields {
            key: "max_concepts"
            value {
              number_value: 20.0
            }
          }
          fields {
            key: "min_value"
            value {
              number_value: 0.0
            }
          }
          fields {
            key: "select_concepts"
            value {
              list_value {
              }
            }
          }
        }
      }
      model_version {
        id: "c0b09e606db94d9bae7eb40c626192fc"
        created_at {
          seconds: 1656524917
          nanos: 276685000
        }
        status {
          code: MODEL_TRAINED
          description: "Model is trained and ready"
        }
        visibility {
          gettable: PUBLIC
        }
        app_id: "text-classification"
        user_id: "erfan"
        metadata {
          fields {
            key: "Model version logs zipped"
            value {
              string_value: "https://s3.amazonaws.com/clarifai-temp/prod/c0b09e606db94d9bae7eb40c626192fc.zip"
            }
          }
        }
      }
      user_id: "erfan"
      input_info {
        fields_map {
          fields {
            key: "text"
            value {
              string_value: "text"
            }
          }
        }
      }
      train_info {
        params {
          fields {
            key: "model_config"
            value {
              struct_value {
                fields {
                  key: "_name_or_path"
                  value {
                    string_value: "distilbert-base-uncased-finetuned-sst-2-english"
                  }
                }
                fields {
                  key: "activation"
                  value {
                    string_value: "gelu"
                  }
                }
                fields {
                  key: "architectures"
                  value {
                    list_value {
                      values {
                        string_value: "DistilBertForSequenceClassification"
                      }
                    }
                  }
                }
                fields {
                  key: "attention_dropout"
                  value {
                    number_value: 0.1
                  }
                }
                fields {
                  key: "dim"
                  value {
                    number_value: 768.0
                  }
                }
                fields {
                  key: "dropout"
                  value {
                    number_value: 0.1
                  }
                }
                fields {
                  key: "finetuning_task"
                  value {
                    string_value: "sst-2"
                  }
                }
                fields {
                  key: "hidden_dim"
                  value {
                    number_value: 3072.0
                  }
                }
                fields {
                  key: "id2label"
                  value {
                    struct_value {
                      fields {
                        key: "0"
                        value {
                          string_value: "NEGATIVE"
                        }
                      }
                      fields {
                        key: "1"
                        value {
                          string_value: "POSITIVE"
                        }
                      }
                    }
                  }
                }
                fields {
                  key: "initializer_range"
                  value {
                    number_value: 0.02
                  }
                }
                fields {
                  key: "label2id"
                  value {
                    struct_value {
                      fields {
                        key: "NEGATIVE"
                        value {
                          number_value: 0.0
                        }
                      }
                      fields {
                        key: "POSITIVE"
                        value {
                          number_value: 1.0
                        }
                      }
                    }
                  }
                }
                fields {
                  key: "max_position_embeddings"
                  value {
                    number_value: 512.0
                  }
                }
                fields {
                  key: "model_type"
                  value {
                    string_value: "distilbert"
                  }
                }
                fields {
                  key: "n_heads"
                  value {
                    number_value: 12.0
                  }
                }
                fields {
                  key: "n_layers"
                  value {
                    number_value: 6.0
                  }
                }
                fields {
                  key: "output_past"
                  value {
                    bool_value: true
                  }
                }
                fields {
                  key: "pad_token_id"
                  value {
                    number_value: 0.0
                  }
                }
                fields {
                  key: "qa_dropout"
                  value {
                    number_value: 0.1
                  }
                }
                fields {
                  key: "seq_classif_dropout"
                  value {
                    number_value: 0.2
                  }
                }
                fields {
                  key: "sinusoidal_pos_embds"
                  value {
                    bool_value: false
                  }
                }
                fields {
                  key: "tie_weights_"
                  value {
                    bool_value: true
                  }
                }
                fields {
                  key: "torch_dtype"
                  value {
                    string_value: "float32"
                  }
                }
                fields {
                  key: "transformers_version"
                  value {
                    string_value: "4.20.0"
                  }
                }
                fields {
                  key: "vocab_size"
                  value {
                    number_value: 30522.0
                  }
                }
              }
            }
          }
          fields {
            key: "tokenizer_config"
            value {
              struct_value {
                fields {
                  key: "cls_token"
                  value {
                    string_value: "[CLS]"
                  }
                }
                fields {
                  key: "do_basic_tokenize"
                  value {
                    bool_value: true
                  }
                }
                fields {
                  key: "do_lower_case"
                  value {
                    bool_value: true
                  }
                }
                fields {
                  key: "mask_token"
                  value {
                    string_value: "[MASK]"
                  }
                }
                fields {
                  key: "model_max_length"
                  value {
                    number_value: 512.0
                  }
                }
                fields {
                  key: "name_or_path"
                  value {
                    string_value: "distilbert-base-uncased-finetuned-sst-2-english"
                  }
                }
                fields {
                  key: "never_split"
                  value {
                    null_value: NULL_VALUE
                  }
                }
                fields {
                  key: "pad_token"
                  value {
                    string_value: "[PAD]"
                  }
                }
                fields {
                  key: "sep_token"
                  value {
                    string_value: "[SEP]"
                  }
                }
                fields {
                  key: "special_tokens_map_file"
                  value {
                    null_value: NULL_VALUE
                  }
                }
                fields {
                  key: "strip_accents"
                  value {
                    null_value: NULL_VALUE
                  }
                }
                fields {
                  key: "tokenize_chinese_chars"
                  value {
                    bool_value: true
                  }
                }
                fields {
                  key: "tokenizer_class"
                  value {
                    string_value: "DistilBertTokenizer"
                  }
                }
                fields {
                  key: "unk_token"
                  value {
                    string_value: "[UNK]"
                  }
                }
              }
            }
          }
        }
      }
      model_type_id: "text-classifier"
      visibility {
        gettable: PUBLIC
      }
      modified_at {
        seconds: 1656525047
        nanos: 842099000
      }
      import_info {
        params {
          fields {
            key: "model_name"
            value {
              string_value: "distilbert-base-uncased-finetuned-sst-2-english"
            }
          }
          fields {
            key: "pipeline_name"
            value {
              string_value: "text-classification"
            }
          }
          fields {
            key: "tokenizer_name"
            value {
              string_value: "distilbert-base-uncased-finetuned-sst-2-english"
            }
          }
          fields {
            key: "toolkit"
            value {
              string_value: "HuggingFace"
            }
          }
        }
      }
    }
    data {
      concepts {
        id: "NEGATIVE"
        name: "NEGATIVE"
        value: 0.9991872906684875
        app_id: "c4660162651d490285bcbfc5aff50bf0"
      }
      concepts {
        id: "POSITIVE"
        name: "POSITIVE"
        value: 0.0008126832544803619
        app_id: "c4660162651d490285bcbfc5aff50bf0"
      }
    }
  }