Update README.md
Browse files
README.md
CHANGED
|
@@ -8,6 +8,9 @@ tags:
|
|
| 8 |
base_model: openai/whisper-small
|
| 9 |
datasets:
|
| 10 |
- mozilla-foundation/common_voice_17_0
|
|
|
|
|
|
|
|
|
|
| 11 |
metrics:
|
| 12 |
- wer
|
| 13 |
model-index:
|
|
@@ -69,7 +72,12 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 69 |
|
| 70 |
# Whisper Small Mixed-Spanish
|
| 71 |
|
| 72 |
-
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 73 |
It achieves the following results on the evaluation set:
|
| 74 |
- Loss: 0.1809
|
| 75 |
- Wer: 8.6345
|
|
@@ -117,4 +125,4 @@ The following hyperparameters were used during training:
|
|
| 117 |
- Transformers 4.42.0.dev0
|
| 118 |
- Pytorch 2.3.0+cu121
|
| 119 |
- Datasets 2.19.1
|
| 120 |
-
- Tokenizers 0.19.1
|
|
|
|
| 8 |
base_model: openai/whisper-small
|
| 9 |
datasets:
|
| 10 |
- mozilla-foundation/common_voice_17_0
|
| 11 |
+
- google/fleurs
|
| 12 |
+
- facebook/multilingual_librispeech
|
| 13 |
+
- facebook/voxpopuli
|
| 14 |
metrics:
|
| 15 |
- wer
|
| 16 |
model-index:
|
|
|
|
| 72 |
|
| 73 |
# Whisper Small Mixed-Spanish
|
| 74 |
|
| 75 |
+
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the es datasets:
|
| 76 |
+
- mozilla-foundation/common_voice_17_0
|
| 77 |
+
- google/fleurs
|
| 78 |
+
- facebook/multilingual_librispeech
|
| 79 |
+
- facebook/voxpopuli
|
| 80 |
+
|
| 81 |
It achieves the following results on the evaluation set:
|
| 82 |
- Loss: 0.1809
|
| 83 |
- Wer: 8.6345
|
|
|
|
| 125 |
- Transformers 4.42.0.dev0
|
| 126 |
- Pytorch 2.3.0+cu121
|
| 127 |
- Datasets 2.19.1
|
| 128 |
+
- Tokenizers 0.19.1
|