Commit
•
8de96ae
1
Parent(s):
d05a746
update model card README.md
Browse files
README.md
CHANGED
|
@@ -1,10 +1,6 @@
|
|
| 1 |
---
|
| 2 |
-
language:
|
| 3 |
-
- ja
|
| 4 |
license: apache-2.0
|
| 5 |
tags:
|
| 6 |
-
- automatic-speech-recognition
|
| 7 |
-
- mozilla-foundation/common_voice_8_0
|
| 8 |
- generated_from_trainer
|
| 9 |
datasets:
|
| 10 |
- common_voice
|
|
@@ -18,10 +14,10 @@ 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
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
-
- Loss: 0.
|
| 24 |
-
- Wer: 2.
|
| 25 |
|
| 26 |
## Model description
|
| 27 |
|
|
@@ -47,15 +43,24 @@ The following hyperparameters were used during training:
|
|
| 47 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
- lr_scheduler_type: linear
|
| 49 |
- lr_scheduler_warmup_steps: 2000
|
| 50 |
-
- num_epochs:
|
| 51 |
- mixed_precision_training: Native AMP
|
| 52 |
|
| 53 |
### Training results
|
| 54 |
|
| 55 |
-
| Training Loss | Epoch | Step
|
| 56 |
-
|
| 57 |
-
| 4.
|
| 58 |
-
| 2.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 59 |
|
| 60 |
|
| 61 |
### Framework versions
|
|
|
|
| 1 |
---
|
|
|
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
tags:
|
|
|
|
|
|
|
| 4 |
- generated_from_trainer
|
| 5 |
datasets:
|
| 6 |
- common_voice
|
|
|
|
| 14 |
|
| 15 |
#
|
| 16 |
|
| 17 |
+
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.5349
|
| 20 |
+
- Wer: 2.6274
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
- lr_scheduler_type: linear
|
| 45 |
- lr_scheduler_warmup_steps: 2000
|
| 46 |
+
- num_epochs: 50.0
|
| 47 |
- mixed_precision_training: Native AMP
|
| 48 |
|
| 49 |
### Training results
|
| 50 |
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 52 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|
|
| 53 |
+
| 4.221 | 4.5 | 1000 | 4.1195 | 2.4024 |
|
| 54 |
+
| 2.3597 | 9.01 | 2000 | 1.1024 | 2.7618 |
|
| 55 |
+
| 1.8795 | 13.51 | 3000 | 0.7498 | 2.5885 |
|
| 56 |
+
| 1.7143 | 18.02 | 4000 | 0.6539 | 2.5976 |
|
| 57 |
+
| 1.6025 | 22.52 | 5000 | 0.5989 | 2.6034 |
|
| 58 |
+
| 1.5403 | 27.03 | 6000 | 0.6035 | 2.6946 |
|
| 59 |
+
| 1.4773 | 31.53 | 7000 | 0.5647 | 2.5558 |
|
| 60 |
+
| 1.4228 | 36.04 | 8000 | 0.5477 | 2.5676 |
|
| 61 |
+
| 1.3801 | 40.54 | 9000 | 0.5413 | 2.6192 |
|
| 62 |
+
| 1.3558 | 45.05 | 10000 | 0.5343 | 2.6575 |
|
| 63 |
+
| 1.3298 | 49.55 | 11000 | 0.5349 | 2.6274 |
|
| 64 |
|
| 65 |
|
| 66 |
### Framework versions
|