Adds support for audio captioning with Whisper #267
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Codecov Report
@@ Coverage Diff @@
## master #267 +/- ##
==========================================
+ Coverage 91.45% 92.26% +0.80%
==========================================
Files 22 22
Lines 620 659 +39
==========================================
+ Hits 567 608 +41
+ Misses 39 37 -2
Partials 14 14
... and 2 files with indirect coverage changes Help us with your feedback. Take ten seconds to tell us how you rate us. Have a feature suggestion? Share it here. |
|
Thank you so much for the PR! 🙌🏻 |
audio.go
Outdated
| @@ -21,6 +28,7 @@ type AudioRequest struct { | |||
| Prompt string // For translation, it should be in English | |||
| Temperature float32 | |||
| Language string // For translation, just do not use it. It seems "en" works, not confirmed... | |||
| Format string | |||
There was a problem hiding this comment.
Let's maybe make typechecker work for us a little bit here?
type AudioResponseFormat string
const (
AudioResponseFormatJSON AudioResponseFormat = "json"
AudioResponseFormatSRT AudioResponseFormat = "srt"
AudioResponseFormatVTT AudioResponseFormat = "vtt"
)
type AudioRequest struct {
...
Format AudioResponseFormat
}
client.go
Outdated
| return decodeResponse(v, *res) | ||
| } | ||
|
|
||
| func decodeResponse(v interface{}, res http.Response) error { |
There was a problem hiding this comment.
Suggested change
| func decodeResponse(v interface{}, res http.Response) error { | |
| func decodeResponse(v any, res http.Response) error { |
There was a problem hiding this comment.
Could we also rename v to something sensible here and in sendRequest, maybe response?
There was a problem hiding this comment.
I have:
- Used
any - Updated
decodeResponsearguments tobody io.Reader, v any- This ordering is a little nicer (input/output)
- I struggled to come up with a good name for
v- this is what is used in thejsonlibrary to mean any value that we will decode into... so I feel like it is a better name than response which is used byhttp(at least in this context)
sashabaranov
approved these changes
Apr 20, 2023
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Closes #143
Allows users to add a
Format:argument to the request to get captions from the audio apis.Demonstration (using the same code added for README)
Screen.Recording.2023-04-19.at.4.13.29.PM.mov
Broke
decodeResponseout of client, because cyclomatic complexity got above 20 with the string response changes.Added tests for
decodeResponseto not decrease code coverage