whisperkittools generated README.md
Browse files
README.md
CHANGED
|
@@ -1,4 +1,18 @@
|
|
| 1 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
We believe that rigorously measuring the "quality of inference" is necessary for developers and
|
| 3 |
enterprises to make informed decisions when opting to use optimized or compressed variants of
|
| 4 |
any machine learning model in production. To contextualize `WhisperKit`, we take the following Whisper
|
|
@@ -47,20 +61,6 @@ evaluation in under 1 hour regardless of the Whisper implementation. Older Apple
|
|
| 47 |
|
| 48 |
|
| 49 |
|
| 50 |
-
---
|
| 51 |
-
pretty_name: "WhisperKit ASR Evaluation Results"
|
| 52 |
-
viewer: false
|
| 53 |
-
tags:
|
| 54 |
-
- whisper
|
| 55 |
-
- whisperkit
|
| 56 |
-
- coreml
|
| 57 |
-
- asr
|
| 58 |
-
- quantized
|
| 59 |
-
---
|
| 60 |
-
# WhisperKit Evaluation Results
|
| 61 |
-
|
| 62 |
-
|
| 63 |
-
|
| 64 |
## Dataset: `librispeech`
|
| 65 |
|
| 66 |
### Quality Evaluation
|
|
|
|
| 1 |
|
| 2 |
+
---
|
| 3 |
+
pretty_name: "WhisperKit ASR Evaluation Results"
|
| 4 |
+
viewer: false
|
| 5 |
+
tags:
|
| 6 |
+
- whisper
|
| 7 |
+
- whisperkit
|
| 8 |
+
- coreml
|
| 9 |
+
- asr
|
| 10 |
+
- quantized
|
| 11 |
+
---
|
| 12 |
+
# WhisperKit Evaluation Results
|
| 13 |
+
|
| 14 |
+
|
| 15 |
+
|
| 16 |
We believe that rigorously measuring the "quality of inference" is necessary for developers and
|
| 17 |
enterprises to make informed decisions when opting to use optimized or compressed variants of
|
| 18 |
any machine learning model in production. To contextualize `WhisperKit`, we take the following Whisper
|
|
|
|
| 61 |
|
| 62 |
|
| 63 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 64 |
## Dataset: `librispeech`
|
| 65 |
|
| 66 |
### Quality Evaluation
|