alex-futo commited on
Commit
ae994ab
·
verified ·
1 Parent(s): c68b8ff

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +24 -0
README.md ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ ---
4
+ # Model Card
5
+
6
+ ## Model Description
7
+
8
+ This is in a fine-tuned series of [OpenAI's Whisper models](https://github.com/openai/whisper).
9
+
10
+ The models have been finetuned for dynamic audio context robustness, allowing shorter audio contexts for better performance with short audio inputs. The method is detailed [in our GitHub repo](https://github.com/futo-org/whisper-acft).
11
+
12
+ - **Developed by:** FUTO
13
+ - **License:** Apache-2.0
14
+ - **Finetuned from model:** OpenAI Whisper
15
+
16
+ ## Uses
17
+
18
+ These models are not useful by themselves under default Whisper runtime configurations.
19
+
20
+ The easiest way to test differing audio context is to use whisper.cpp with the `--audio-context` parameter. We provide converted whisper.cpp models in our [GitHub README](https://github.com/futo-org/whisper-acft?tab=readme-ov-file#finetuning-whisper-for-dynamic-audio-context-robustness).
21
+
22
+ ## Other Information
23
+
24
+ More information can be found in our [GitHub README](https://github.com/futo-org/whisper-acft?tab=readme-ov-file#finetuning-whisper-for-dynamic-audio-context-robustness).