asr speech recognition example #2047
Conversation
Codecov Report
@@ Coverage Diff @@
## master #2047 +/- ##
=======================================
Coverage 72.71% 72.71%
=======================================
Files 79 79
Lines 3742 3742
Branches 58 58
=======================================
Hits 2721 2721
Misses 1017 1017
Partials 4 4 📣 We’re building smart automated test selection to slash your CI/CD build times. Learn more |
| if isinstance(data, list): | ||
| data = data[0] | ||
| data = data.get("data") or data.get("body") |
There was a problem hiding this comment.
This is not able to handle batching. ref example
There was a problem hiding this comment.
To be fair neither does our default handler , for an example I think this is fine
There was a problem hiding this comment.
For audio models, batching may not make sense in all cases. Will be good to mention as a note in the readme that this example does not support batching and verify the config properties match
| if isinstance(data, list): | ||
| data = data[0] | ||
| data = data.get("data") or data.get("body") |
There was a problem hiding this comment.
For audio models, batching may not make sense in all cases. Will be good to mention as a note in the readme that this example does not support batching and verify the config properties match
Description
Provides an example of ASR (automated speech recognition) model serving.
Input is a wav file; output text translation of that wav.
Type of change
Please delete options that are not relevant.
Checklist: