Mantieni tutto organizzato con le raccolte
Salva e classifica i contenuti in base alle tue preferenze.
Utilizza un modello Custom Speech-to-Text addestrato nella tua applicazione di produzione o nei flussi di lavoro di benchmarking. Non appena esegui il deployment del modello tramite un endpoint dedicato, ottieni automaticamente l'accesso programmatico tramite un oggetto di riconoscimento, che può essere utilizzato direttamente tramite l'API Speech-to-Text V2 o nella console Google Cloud .
Prima di iniziare
Assicurati di aver creato un account Google Cloud , un progetto, addestrato un modello vocale personalizzato e di averne eseguito il deployment utilizzando un endpoint.
Esegui l'inferenza in V2
Affinché un modello Custom Speech-to-Text sia pronto per l'uso, lo stato del modello nella scheda Modelli deve essere Attivo e l'endpoint dedicato nella scheda Endpoint deve essere Eseguito il deployment.
Nel nostro esempio, in cui l'ID progetto Google Cloud è custom-models-walkthrough, l'endpoint corrispondente al modello Speech-to-Text personalizzato quantum-computing-lectures-custom-model è quantum-computing-lectures-custom-model-prod-endpoint. La regione in cui è disponibile è us-east1 e la richiesta di trascrizione batch è la seguente:
fromgoogle.api_coreimportclient_optionsfromgoogle.cloud.speech_v2importSpeechClientfromgoogle.cloud.speech_v2.typesimportcloud_speechdefquickstart_v2(project_id:str,audio_file:str,)-> cloud_speech.RecognizeResponse:"""Transcribe an audio file."""# Instantiates a clientclient=SpeechClient(client_options=client_options.ClientOptions(api_endpoint="us-east1-speech.googleapis.com"))# Reads a file as byteswithopen(audio_file,"rb")asf:content=f.read()config=cloud_speech.RecognitionConfig(auto_decoding_config=cloud_speech.AutoDetectDecodingConfig(),language_codes=["en-US"],model="projects/custom-models-walkthrough/locations/us-east1/endpoints/quantum-computing-lectures-custom-model-prod-endpoint",)request=cloud_speech.RecognizeRequest(recognizer=f"projects/custom-models-walkthrough/locations/us-east1/recognizers/_",config=config,content=content,)# Transcribes the audio into textresponse=client.recognize(request=request)forresultinresponse.results:print(f"Transcript: {result.alternatives[0].transcript}")returnresponse
[[["Facile da capire","easyToUnderstand","thumb-up"],["Il problema è stato risolto","solvedMyProblem","thumb-up"],["Altra","otherUp","thumb-up"]],[["Difficile da capire","hardToUnderstand","thumb-down"],["Informazioni o codice di esempio errati","incorrectInformationOrSampleCode","thumb-down"],["Mancano le informazioni o gli esempi di cui ho bisogno","missingTheInformationSamplesINeed","thumb-down"],["Problema di traduzione","translationIssue","thumb-down"],["Altra","otherDown","thumb-down"]],["Ultimo aggiornamento 2025-09-04 UTC."],[],[],null,["# Use models\n\n| **Preview**\n|\n|\n| This feature is subject to the \"Pre-GA Offerings Terms\" in the General Service Terms section\n| of the [Service Specific Terms](/terms/service-terms#1).\n|\n| Pre-GA features are available \"as is\" and might have limited support.\n|\n| For more information, see the\n| [launch stage descriptions](/products#product-launch-stages).\n\nUse a trained Custom Speech-to-Text model in your production application or benchmarking workflows. As soon as you deploy your model through a dedicated endpoint, you automatically get programmatic access through a recognizer object, which can be used directly through the Speech-to-Text V2 API or in the Google Cloud console.\n\nBefore you begin\n----------------\n\nEnsure you have signed up for a Google Cloud account, created a project, trained a custom speech model, and deployed it using an endpoint.\n\nPerform inference in V2\n-----------------------\n\nFor a Custom Speech-to-Text model to be ready for use, the state of the model in the **Models** tab should be **Active** , and the dedicated endpoint in the **Endpoints** tab must be **Deployed**.\n\nIn our example, where a Google Cloud project ID is `custom-models-walkthrough`, the endpoint that corresponds to the Custom Speech-to-Text model `quantum-computing-lectures-custom-model` is `quantum-computing-lectures-custom-model-prod-endpoint`. The region that it's available is `us-east1`, and the batch transcription request is the following: \n\n from google.api_core import client_options\n from google.cloud.speech_v2 import SpeechClient\n from google.cloud.speech_v2.types import cloud_speech\n\n def quickstart_v2(\n project_id: str,\n audio_file: str,\n ) -\u003e cloud_speech.RecognizeResponse:\n \"\"\"Transcribe an audio file.\"\"\"\n # Instantiates a client\n client = SpeechClient(\n client_options=client_options.ClientOptions(\n api_endpoint=\"us-east1-speech.googleapis.com\"\n )\n )\n\n # Reads a file as bytes\n with open(audio_file, \"rb\") as f:\n content = f.read()\n\n config = cloud_speech.RecognitionConfig(\n auto_decoding_config=cloud_speech.https://cloud.google.com/python/docs/reference/speech/latest/google.cloud.speech_v2.types.AutoDetectDecodingConfig.html(),\n language_codes=[\"en-US\"],\n model=\"projects/custom-models-walkthrough/locations/us-east1/endpoints/quantum-computing-lectures-custom-model-prod-endpoint\",\n )\n request = cloud_speech.RecognizeRequest(\n recognizer=f\"projects/custom-models-walkthrough/locations/us-east1/recognizers/_\",\n config=config,\n content=content,\n )\n\n # Transcribes the audio into text\n response = client.https://cloud.google.com/python/docs/reference/speech/latest/google.cloud.speech_v1.services.speech.SpeechClient.html#google_cloud_speech_v1_services_speech_SpeechClient_recognize(request=request)\n\n for result in response.results:\n print(f\"Transcript: {result.alternatives[0].transcript}\")\n\n return response\n\n| **Note:** If you try to create a recognizer object in a different region than the one that the endpoint is created in, the request will fail.\n\nWhat's next\n-----------\n\nFollow the resources to take advantage of custom speech models in your application. See [Evaluate your custom models](/speech-to-text/v2/docs/custom-speech-models/evaluate-model)."]]