issues
search
sul-dlss
/
speech-to-text
Tools for generating transcript and caption files from media files (e.g. a Docker container for running Whisper on video files in AWS ECS? 🤷🏽)
0
stars
0
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
File specific language specification
#51
edsu
opened
1 day ago
0
Check media and log attributes
#50
edsu
closed
17 hours ago
1
speech_to_text.py should check to see whether a file contains audio before processing it with whisper
#48
jmartin-sul
closed
17 hours ago
0
Whisper output quality: test transcription of video where most of speech is German, but opening 30ish seconds of speech is English
#47
jmartin-sul
closed
1 week ago
2
Build and deploy speech-to-text
#46
edsu
opened
1 week ago
0
When using Whisper's auto-detected language, insert that language into the Cocina
#45
andrewjbtw
closed
5 days ago
2
[HOLD] only need vtt and txt files in output
#42
peetucket
closed
1 week ago
3
Whisper should only produce .txt and .vtt files
#41
peetucket
closed
1 week ago
1
Add type checking
#40
edsu
closed
3 weeks ago
0
Mocked AWS & Github Action
#39
edsu
closed
4 weeks ago
0
Stanza API docs review
#38
laurensorensen
opened
1 month ago
5
API docs overview -- how does the file return to us via the Amara API?
#37
laurensorensen
closed
1 month ago
1
finish up CI configuration
#36
jmartin-sul
closed
3 weeks ago
0
Investigate Whisper.writer parameters
#35
alundgard
opened
1 month ago
1
Simplify bucket and job message
#34
edsu
closed
1 month ago
0
Adjust locations for AWS Whisper Container
#33
peetucket
closed
1 month ago
1
write DevOpsDocs for speech-to-text infrastructure
#32
jmartin-sul
opened
1 month ago
0
Log media size and duration
#31
edsu
closed
17 hours ago
0
Added logging and removed caching
#30
edsu
closed
1 month ago
0
Improve logging
#29
edsu
closed
1 month ago
0
ExpiredToken when calling the ReceiveMessage
#28
edsu
closed
1 month ago
0
Add Honeybadger
#27
edsu
opened
1 month ago
0
Add new Turbo model
#26
edsu
closed
1 month ago
0
minor enhancements: return technical metadata, allow job ID specification for testing
#25
jmartin-sul
closed
1 month ago
4
speech-to-text worker sends back some basic technical metadata in the body of the done message it queues
#24
jmartin-sul
closed
1 month ago
0
should we automatically update the model files that whisper uses? if so, at what frequency and with what mechanism?
#23
jmartin-sul
opened
1 month ago
2
small readme and comment touchups
#22
jmartin-sul
closed
1 month ago
1
DONE message should include output file
#21
edsu
closed
3 weeks ago
1
TODO job should just include ID
#20
edsu
closed
1 month ago
1
Run tests as Github Action
#12
edsu
closed
4 weeks ago
0
Add initial Docker container
#9
edsu
closed
1 month ago
0
Finish skeleton common-accessioning robot and workflow def for... `captionWF`? `speechToTextWF`? [final name TBD]
#8
jmartin-sul
closed
2 months ago
1
Productionize speech_to_text_generation_service, or get it as close as possible and ticket the remaining work
#7
jmartin-sul
opened
2 months ago
0
provision S3 buckets and credentials for temp space to hold 1) the incoming content to run through speech-to-text generation, and 2) the generated transcript/caption files.
#6
jmartin-sul
closed
2 months ago
3
Questions surrounding speech_to_text_generation_service (e.g., do we need a speech_to_text_request_service REST API?)
#5
jmartin-sul
closed
2 months ago
1
[investigate/prototype] speech_to_text_generation_service approach 2: Explore AWS SageMaker
#4
jmartin-sul
opened
2 months ago
2
[investigate/prototype] speech_to_text_generation_service approach 1: Define a Docker container for running open source Whisper in a container that we define and for which we manage deployment (lives in this repo?)
#3
jmartin-sul
closed
1 month ago
2
Choose an approach for producing speech-to-text output, given media file input (let's call this speech_to_text_generation_service for now?)
#2
jmartin-sul
opened
2 months ago
0
[EPIC] Prototype workflow for generating and accessioning speech-to-text extraction
#1
jmartin-sul
opened
2 months ago
0