Sagicc commited on
Commit
fdce795
1 Parent(s): 5dbbaad

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -3
README.md CHANGED
@@ -7,6 +7,7 @@ tags:
7
  - generated_from_trainer
8
  datasets:
9
  - mozilla-foundation/common_voice_13_0
 
10
  metrics:
11
  - wer
12
  model-index:
@@ -32,7 +33,7 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  # Whisper Large v3 cmb
34
 
35
- This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the Common Voice 13 dataset.
36
  It achieves the following results on the evaluation set:
37
  - Loss: 0.1111
38
  - Wer Ortho: 0.1339
@@ -40,7 +41,11 @@ It achieves the following results on the evaluation set:
40
 
41
  ## Model description
42
 
43
- More information needed
 
 
 
 
44
 
45
  ## Intended uses & limitations
46
 
@@ -81,4 +86,4 @@ The following hyperparameters were used during training:
81
  - Transformers 4.35.2
82
  - Pytorch 2.0.1+cu117
83
  - Datasets 2.14.5
84
- - Tokenizers 0.14.1
 
7
  - generated_from_trainer
8
  datasets:
9
  - mozilla-foundation/common_voice_13_0
10
+ - google/fleurs
11
  metrics:
12
  - wer
13
  model-index:
 
33
 
34
  # Whisper Large v3 cmb
35
 
36
+ This model is a fine-tuned version of [openai/whisper-larhe-v3](https://huggingface.co/openai/whisper-large-v3) on the Common Voice 13, Google Fleurs and juzne vesti dataset.
37
  It achieves the following results on the evaluation set:
38
  - Loss: 0.1111
39
  - Wer Ortho: 0.1339
 
41
 
42
  ## Model description
43
 
44
+ Dataset Juzne vesti is published by
45
+
46
+ Rupnik, Peter and Ljubešić, Nikola, 2022,\
47
+ ASR training dataset for Serbian JuzneVesti-SR v1.0, Slovenian language resource repository CLARIN.SI, ISSN 2820-4042,\
48
+ http://hdl.handle.net/11356/1679.
49
 
50
  ## Intended uses & limitations
51
 
 
86
  - Transformers 4.35.2
87
  - Pytorch 2.0.1+cu117
88
  - Datasets 2.14.5
89
+ - Tokenizers 0.14.1