Commit
•
27a0217
1
Parent(s):
35332a7
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,104 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: cc-by-nc-4.0
|
| 3 |
+
base_model: facebook/mms-1b-all
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- audiofolder
|
| 8 |
+
metrics:
|
| 9 |
+
- wer
|
| 10 |
+
model-index:
|
| 11 |
+
- name: wav2vec2-large-mms-1b-all-lingala-ojpl
|
| 12 |
+
results:
|
| 13 |
+
- task:
|
| 14 |
+
name: Automatic Speech Recognition
|
| 15 |
+
type: automatic-speech-recognition
|
| 16 |
+
dataset:
|
| 17 |
+
name: audiofolder
|
| 18 |
+
type: audiofolder
|
| 19 |
+
config: default
|
| 20 |
+
split: train
|
| 21 |
+
args: default
|
| 22 |
+
metrics:
|
| 23 |
+
- name: Wer
|
| 24 |
+
type: wer
|
| 25 |
+
value: 0.2697881828316611
|
| 26 |
+
---
|
| 27 |
+
|
| 28 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 29 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 30 |
+
|
| 31 |
+
# wav2vec2-large-mms-1b-all-lingala-ojpl
|
| 32 |
+
|
| 33 |
+
This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on the audiofolder dataset.
|
| 34 |
+
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.8394
|
| 36 |
+
- Wer: 0.2698
|
| 37 |
+
|
| 38 |
+
## Model description
|
| 39 |
+
|
| 40 |
+
More information needed
|
| 41 |
+
|
| 42 |
+
## Intended uses & limitations
|
| 43 |
+
|
| 44 |
+
More information needed
|
| 45 |
+
|
| 46 |
+
## Training and evaluation data
|
| 47 |
+
|
| 48 |
+
More information needed
|
| 49 |
+
|
| 50 |
+
## Training procedure
|
| 51 |
+
|
| 52 |
+
### Training hyperparameters
|
| 53 |
+
|
| 54 |
+
The following hyperparameters were used during training:
|
| 55 |
+
- learning_rate: 0.001
|
| 56 |
+
- train_batch_size: 1
|
| 57 |
+
- eval_batch_size: 8
|
| 58 |
+
- seed: 42
|
| 59 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 60 |
+
- lr_scheduler_type: linear
|
| 61 |
+
- lr_scheduler_warmup_steps: 100
|
| 62 |
+
- num_epochs: 4
|
| 63 |
+
|
| 64 |
+
### Training results
|
| 65 |
+
|
| 66 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 67 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 68 |
+
| 0.5442 | 0.13 | 100 | 0.9396 | 0.3307 |
|
| 69 |
+
| 0.9882 | 0.27 | 200 | 0.9189 | 0.3389 |
|
| 70 |
+
| 0.5845 | 0.4 | 300 | 0.9322 | 0.3129 |
|
| 71 |
+
| 0.4162 | 0.54 | 400 | 1.0742 | 0.2939 |
|
| 72 |
+
| 0.506 | 0.67 | 500 | 0.9626 | 0.3077 |
|
| 73 |
+
| 0.8789 | 0.81 | 600 | 1.0502 | 0.3055 |
|
| 74 |
+
| 0.6166 | 0.94 | 700 | 0.9560 | 0.2984 |
|
| 75 |
+
| 0.4101 | 1.08 | 800 | 0.9520 | 0.2995 |
|
| 76 |
+
| 0.6536 | 1.21 | 900 | 1.1213 | 0.2988 |
|
| 77 |
+
| 0.4921 | 1.34 | 1000 | 1.0319 | 0.3010 |
|
| 78 |
+
| 0.856 | 1.48 | 1100 | 0.9514 | 0.3043 |
|
| 79 |
+
| 0.4479 | 1.61 | 1200 | 0.9079 | 0.2843 |
|
| 80 |
+
| 0.7249 | 1.75 | 1300 | 0.9612 | 0.2895 |
|
| 81 |
+
| 0.5384 | 1.88 | 1400 | 0.9050 | 0.2928 |
|
| 82 |
+
| 0.709 | 2.02 | 1500 | 0.9844 | 0.2735 |
|
| 83 |
+
| 0.6575 | 2.15 | 1600 | 0.9377 | 0.2772 |
|
| 84 |
+
| 0.6115 | 2.28 | 1700 | 0.9690 | 0.2876 |
|
| 85 |
+
| 0.3119 | 2.42 | 1800 | 0.9222 | 0.2798 |
|
| 86 |
+
| 0.3591 | 2.55 | 1900 | 0.9358 | 0.2783 |
|
| 87 |
+
| 0.3979 | 2.69 | 2000 | 0.9156 | 0.2702 |
|
| 88 |
+
| 0.7541 | 2.82 | 2100 | 0.8838 | 0.2761 |
|
| 89 |
+
| 0.81 | 2.96 | 2200 | 0.8460 | 0.2813 |
|
| 90 |
+
| 0.2224 | 3.09 | 2300 | 0.9377 | 0.2694 |
|
| 91 |
+
| 0.2338 | 3.23 | 2400 | 0.8870 | 0.2746 |
|
| 92 |
+
| 0.5315 | 3.36 | 2500 | 0.8782 | 0.2672 |
|
| 93 |
+
| 0.4045 | 3.49 | 2600 | 0.8811 | 0.2653 |
|
| 94 |
+
| 0.4874 | 3.63 | 2700 | 0.9059 | 0.2620 |
|
| 95 |
+
| 0.304 | 3.76 | 2800 | 0.8801 | 0.2690 |
|
| 96 |
+
| 1.4688 | 3.9 | 2900 | 0.8394 | 0.2698 |
|
| 97 |
+
|
| 98 |
+
|
| 99 |
+
### Framework versions
|
| 100 |
+
|
| 101 |
+
- Transformers 4.32.0.dev0
|
| 102 |
+
- Pytorch 1.13.1+cu117
|
| 103 |
+
- Datasets 2.13.1
|
| 104 |
+
- Tokenizers 0.13.3
|