How to disable sentence-level auto correction in Google Cloud Speech-to-Text API
I am working on a speech recognition task, which involves the detection of children's speaking capability, improvement over time...
I'd like to use the Google Cloud Speech to Text API for the ASR part of the detection. Then I would use the transcripts of different measurements to estimate the advancement.
But! The sentence level autocorrect of Google Speech API consistently rewrites the previous limb of the spoken sentence...
Is there a way to disable the autocorrect of this ASR?
I can't bypass this problem with the "speechContext", "single_utterance" or "maxAlternatives" options.
"single_utterance" may work with words, but it corrects the misspells..
Any advice in this field?
If you use streaming instead of batch recognize, you should receive an answer as soon as that part of the audio is transcribed, it does not wait for the rest of the sentence. You should then just store the first answer provided by the stream, not the further corrections.
This means that you don't have to wait until isFinal=True.
For a quick and dirty example of what I mean, go tho the speech API page, and run the streaming test with the developer tools open. There you'll see the streaming data received as the words are being spoken:
- TypeError: __call__() missing 1 required positional argument: 'context' error when deploying on GCP
- Why GCP loadbalancer frontend has only two ports enabled?
- New Google place api using google OAuth, ask failed to refresh token
- Is it possible to display context of the search result in gcp logging
- Is there float32 precision on Google TPU?
- BigQuery : is it possible to iterate over an array?
- oauth 2 parameters can only have a single value: scope
- Correct use of gcloud --sort-by combined with --limit
- Is PIVOT Operator supported in Big Query Materialized view?
- App attestation failed with Firebase App check in release on Android
- Why doesn't the offline cloud firestore documentation have code for offline query indexes for flutter?
- _CHANGE_TYPE not working when streaming Google Big Query rows from Pub/Sub
- Migrating from legacy Google FCM to HTTP v1 for push notifications
- Google OAuth 2 Error 400: redirect_uri_mismatch but redirect uri is compliant and already registered in Google Cloud Console
- Can we update a field due to its value without reading it in firebase?
- Use process.env variables inside next.config.js
- What is the best practice for decoding Firestore documents in a listener for Swift 5?
- How to install Google Cloud SDK app-engine-python on Debian 12?
- Bigquery service account restricted to a dataset
- Gcloud Pub/Sub: Total timeout of API google.pubsub.v1.Publisher exceeded 60000 milliseconds before any response was received
- Keep getting the error Google Sign-In Error: PlatformException(sign_in_failed, com.google.android.gms.common.api.ApiException: 10: , null, null)
- Error 400 invalid JSON Payload Unknown name generationConfig on an AI API Curl command
- How to access cloud run environment variables in Dockerfile
- Error 400: Invalid JSON payload received when calling Google Generative Language API
- GCP Bucket Permissions by Prefix
- database connection URI string for GCP cloudsql postgres database?
- Who control Google Cloud platform filtering?
- gcloud cli command create eventarc errors
- Is there a way to block HTTP on GCP AppEngine
- How to generate GOOGLE_CLIENT_ID and GOOGLE_CLIENT_SECRET without a domain?