Update README.md
Browse files
README.md
CHANGED
@@ -7,6 +7,8 @@ tags:
|
|
7 |
base_model: openai/whisper-base
|
8 |
datasets:
|
9 |
- mozilla-foundation/common_voice_17_0
|
|
|
|
|
10 |
metrics:
|
11 |
- wer
|
12 |
model-index:
|
@@ -54,9 +56,13 @@ model-index:
|
|
54 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
55 |
should probably proofread and complete it, then remove this comment. -->
|
56 |
|
57 |
-
# Whisper
|
|
|
|
|
|
|
|
|
|
|
58 |
|
59 |
-
This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the Common Voice 17.0 dataset.
|
60 |
It achieves the following results on the evaluation set:
|
61 |
- Loss: 0.5065
|
62 |
- Wer: 19.9389
|
@@ -103,4 +109,4 @@ The following hyperparameters were used during training:
|
|
103 |
- Transformers 4.42.0.dev0
|
104 |
- Pytorch 2.3.0+cu121
|
105 |
- Datasets 2.19.1
|
106 |
-
- Tokenizers 0.19.1
|
|
|
7 |
base_model: openai/whisper-base
|
8 |
datasets:
|
9 |
- mozilla-foundation/common_voice_17_0
|
10 |
+
- google/fleurs
|
11 |
+
- facebook/voxpopuli
|
12 |
metrics:
|
13 |
- wer
|
14 |
model-index:
|
|
|
56 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
57 |
should probably proofread and complete it, then remove this comment. -->
|
58 |
|
59 |
+
# Whisper base mixed-English
|
60 |
+
|
61 |
+
This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the "en" datasets:
|
62 |
+
- mozilla-foundation/common_voice_17_0
|
63 |
+
- google/fleurs
|
64 |
+
- facebook/voxpopuli
|
65 |
|
|
|
66 |
It achieves the following results on the evaluation set:
|
67 |
- Loss: 0.5065
|
68 |
- Wer: 19.9389
|
|
|
109 |
- Transformers 4.42.0.dev0
|
110 |
- Pytorch 2.3.0+cu121
|
111 |
- Datasets 2.19.1
|
112 |
+
- Tokenizers 0.19.1
|