eb738a1552
Fix for Whisper Error: 'File is not defined' when using Speech to Text ( #2526 )
...
* tested ok
* update localai stt file
* update toFile method for OpenAI Assistant uploads
---------
Co-authored-by: Henry Heng <henryheng@flowiseai.com >
Co-authored-by: Henry <hzj94@hotmail.com >
2024-05-30 12:54:55 +01:00
d3f03e380e
[FEATURE] Added support for LocalAI Speech To Text configuration ( #2376 )
...
* Added support for LocalAI to the Speech To Text configuration. Added a few debug statements around speech to text conversion. Finally, refactored the speechToTextProviders a bit to try and remove some magic strings that have undocumented rules around naming.
* LocalAI STT - PR Feedback - Updated LocalAI Image, changed casing, and updated the default model to whisper-1.
2024-05-13 12:21:27 +01:00
7006d64de0
Feature/s3 storage ( #2226 )
...
* centralizing file writing....
* allowing s3 as storage option
* allowing s3 as storage option
* update s3 storage
---------
Co-authored-by: Henry <hzj94@hotmail.com >
2024-04-23 11:35:38 +01:00
6bd8aaefc8
Bugfix/speech input on Safari/iOS ( #1971 )
...
* debug to identify
* Safari sends audio file as mp4 and nor webp
* Safari on iOS needs special handling
* lint fixes
* updated condition
* Remove unused import
---------
Co-authored-by: Ilango <rajagopalilango@gmail.com >
2024-04-19 01:28:09 +01:00
041bfea940
add more params
2024-02-02 20:07:50 +00:00
9cd0362f24
Merge branch 'main' into FEATURE/Vision
...
# Conflicts:
# packages/components/nodes/chains/ConversationChain/ConversationChain.ts
# packages/server/src/index.ts
# packages/server/src/utils/index.ts
2024-02-02 02:54:06 +00:00
e81927ee13
SpeechToText: Adding SpeechToText at the Chatflow level.
2024-01-31 07:48:38 -05:00
Rafael Reis