Better description
Browse files
README.md
CHANGED
|
@@ -1,4 +1,4 @@
|
|
| 1 |
-
---
|
| 2 |
license: apache-2.0
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
|
@@ -27,7 +27,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 27 |
|
| 28 |
# openai/whisper-medium
|
| 29 |
|
| 30 |
-
This model
|
|
|
|
|
|
|
| 31 |
It achieves the following results on the evaluation set:
|
| 32 |
- Loss: 0.2029
|
| 33 |
- Wer: 8.3235
|
|
|
|
| 1 |
+
+---
|
| 2 |
license: apache-2.0
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
|
|
|
| 27 |
|
| 28 |
# openai/whisper-medium
|
| 29 |
|
| 30 |
+
This is an automatic speech recognition model that also does punctuation and casing. Vegeu [projecte de millora dels models Whisper](https://www.softcatala.org/projectes/millora-del-catala-dels-models-del-reconeixement-de-la-parla-whisper/) (Catalan).
|
| 31 |
+
|
| 32 |
+
This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the mozilla-foundation/common_voice_11_0 ca dataset.
|
| 33 |
It achieves the following results on the evaluation set:
|
| 34 |
- Loss: 0.2029
|
| 35 |
- Wer: 8.3235
|