Commit @9922993c507f1df9eea6eb6be0653bb7a3ddfe63 - yjyoon/whisper_server

Fedir Zadniprovskyi 01-12

docs: add TODOs

@9922993c507f1df9eea6eb6be0653bb7a3ddfe63

59bd630

9922993

docs/introduction.md

--- docs/introduction.md

+++ docs/introduction.md


 !!! note
 
-    This project was previously named `faster-whisper-server`. It has been renamed to `speaches` to ...
+    This project was previously named `faster-whisper-server`. I've decided to change the name from `faster-whisper-server`, as the project has evolved to support more than just transcription.
+
+!!! note
+
+    These docs are a work in progress. If you have any questions, suggestions, or find a bug, please create an issue.
 
 TODO: add HuggingFace Space URL
 

9922993

docs/usage/dynamic-loading.md (added)

+++ docs/usage/dynamic-loading.md

...	...	@@ -0,0 +1,6 @@
	1	+https://github.com/vllm-project/vllm/issues/5491
	2	+https://medium.com/@noel.B/preventing-model-swapping-in-ollama-a-guide-to-persistent-loading-f81f1dfb858d
	3	+
	4	+TODO: warn about some space still being used
	5	+TODO: mention that it's inspired by ollama
	6	+TODO: mention that un like ollama it supports keeping multiple models loaded

59bd630

9922993

docs/usage/live-transcription.md

--- docs/usage/live-transcription.md

+++ docs/usage/live-transcription.md

...	...	@@ -1,3 +1,5 @@
	1	+TODO: live vs streaming
	2	+
1	3	## Live Transcription (using WebSocket)
2	4
3	5	!!! note

59bd630

9922993

docs/usage/speech-to-text.md

--- docs/usage/speech-to-text.md

+++ docs/usage/speech-to-text.md


 TODO: mention streaming
 TODO: add a demo
 TODO: talk about audio format
+TODO: add a note about performance
+TODO: add a note about vad
 
 !!! note
 

59bd630

9922993

docs/usage/text-to-speech.md

--- docs/usage/text-to-speech.md

+++ docs/usage/text-to-speech.md


 http://localhost:8001/faster-whisper-server/api/
 TODO: add a note about automatic downloads
 TODO: add a demo
+TODO: add a note about tts only running on cpu
+TODO: add a note about exploring other models
+TODO: add a note about performance
 
 !!! note
 

Add a comment

Open 0
Closed 0

List

...	...	@@ -1,6 +1,10 @@
1	1	!!! note
2	2
3		- This project was previously named `faster-whisper-server`. It has been renamed to `speaches` to ...
	3	+ This project was previously named `faster-whisper-server`. I've decided to change the name from `faster-whisper-server`, as the project has evolved to support more than just transcription.
	4	+
	5	+!!! note
	6	+
	7	+ These docs are a work in progress. If you have any questions, suggestions, or find a bug, please create an issue.
4	8
5	9	TODO: add HuggingFace Space URL
6	10

...	...	@@ -2,6 +2,8 @@
2	2	TODO: mention streaming
3	3	TODO: add a demo
4	4	TODO: talk about audio format
	5	+TODO: add a note about performance
	6	+TODO: add a note about vad
5	7
6	8	!!! note
7	9

...	...	@@ -5,6 +5,9 @@
5	5	http://localhost:8001/faster-whisper-server/api/
6	6	TODO: add a note about automatic downloads
7	7	TODO: add a demo
	8	+TODO: add a note about tts only running on cpu
	9	+TODO: add a note about exploring other models
	10	+TODO: add a note about performance
8	11
9	12	!!! note
10	13

Delete comment