Skip to content

Update transcriptions docs#3961

Open
michalkulakowski wants to merge 1 commit intomainfrom
mkulakow/update_trasncritpions_demo
Open

Update transcriptions docs#3961
michalkulakowski wants to merge 1 commit intomainfrom
mkulakow/update_trasncritpions_demo

Conversation

@michalkulakowski
Copy link
Collaborator

🛠 Summary

JIRA/Issue if applicable.
Describe the changes.

🧪 Checklist

  • Unit tests added.
  • The documentation updated.
  • Change follows security best practices.
    ``



```bash
curl http://localhost:8000/v3/audio/transcriptions -H "Content-Type: multipart/form-data" -F file="@speech.wav" -F model="openai/whisper-large-v3-turbo" -F language="en" -F timestamp_granularities[]="segment"
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

should we demo word timestamp granularities as well? I dont see it here

```
:::

**Note:** To enable word timestamps, edit `$(pwd)/models/openai/whisper-large-v3-turbo/graph.pbtxt` by adding `enable_word_timestamps: true`:
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Do we want to support this setting in export_model script and via CLI pull?

```
:::

**Note:** To enable word timestamps, edit `$(pwd)/models/openai/whisper-large-v3-turbo/graph.pbtxt` by adding `enable_word_timestamps: true`:
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

should it be part of export_models.py and ovms_cli? Why this is needed while the client request has such parameter?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants