Creating a Transcription Job
Create and submit a Speech job to transcribe one or more media files to text files.
Before you begin:
Store media the files that you want to transcribe in an Object Storage bucket in a tenancy.
The Whisper model is trained on a large corpus of multilingual data collected from the web and supports file based voice to text transcription for 50+ languages. This model uses the same service end points and API/SDK interfaces as the Oracle speech model to give you the most flexibility and compatibility. In addition, the Whisper model uses diarization to label individual speakers in the recording.
To compare Whisper and Oracle ASR models for transcription job creating, see Comparing Whisper and Oracle ASR Models.
Comparing Whisper and Oracle ASR Models
Compare Whisper model and Oracle ASR model for creating transcription jobs.
Use the following comparison table of the Whisper model vs the Oracle ASR model to choose the correct model when creating a transcription job.
Feature | Oracle ASR model | Whisper Model in Oracle Speech Service |
---|---|---|
Real time transcriptions | Supported | Not supported |
Large file size | Up to 2 GB | Up to 2 GB |
Word level timestamp | Supported | Supported |
File format | AAC, AC3, AMR, AU, FLAC, M4A, MKV, MP3, MP4, OGA, OGG, WAV, WEBM | AAC, AC3, AMR, AU, FLAC, M4A, MKV, MP3, MP4, OGA, OGG, WAV, WEBM |
Multilingual support | English, Spanish, French, German, Italian, Portuguese, and Hindi | Same as Oracle ASR model plus 50 other languages* |
Diarization | Supported | Supported |
Store the media file that you want to transcribe. Use the create command and required parameters to create a transcription job.
oci speech transcription-job create [OPTIONS]
Avoid entering confidential information.
For a complete list of flags and variable options for CLI commands, see the CLI Command Reference.
Use the CreateTranscriptionJob and ChangeTranscriptionJobCompartment operations to create a job.