Merge branch 'main' of https://huggingface.co/hf-test/xls-r-300m-sv into main
Browse files
README.md
CHANGED
@@ -16,7 +16,7 @@ model-index:
|
|
16 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
should probably proofread and complete it, then remove this comment. -->
|
18 |
|
19 |
-
#
|
20 |
|
21 |
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the MOZILLA-FOUNDATION/COMMON_VOICE_7_0 - SV-SE dataset.
|
22 |
It achieves the following results on the evaluation set:
|
@@ -99,7 +99,13 @@ The following hyperparameters were used during training:
|
|
99 |
- Datasets 1.17.1.dev0
|
100 |
- Tokenizers 0.10.3
|
101 |
|
102 |
-
###
|
103 |
|
104 |
|
105 |
-
###
|
|
|
|
|
|
|
|
|
|
|
|
|
|
16 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
should probably proofread and complete it, then remove this comment. -->
|
18 |
|
19 |
+
# XLS-R-300m-SV
|
20 |
|
21 |
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the MOZILLA-FOUNDATION/COMMON_VOICE_7_0 - SV-SE dataset.
|
22 |
It achieves the following results on the evaluation set:
|
|
|
99 |
- Datasets 1.17.1.dev0
|
100 |
- Tokenizers 0.10.3
|
101 |
|
102 |
+
### Inference Without Decoder
|
103 |
|
104 |
|
105 |
+
### Inference With Decoder
|
106 |
+
|
107 |
+
|
108 |
+
### Eval results (run `./eval.py`) on Common Voice 7 "test":
|
109 |
+
|
110 |
+
**Without LM**: 27.28 WER
|
111 |
+
**With LM**:
|