Model save
Browse files- README.md +111 -0
- model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,111 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: cc-by-nc-4.0
|
| 3 |
+
base_model: facebook/mms-1b-all
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- common_voice_16_0
|
| 8 |
+
metrics:
|
| 9 |
+
- wer
|
| 10 |
+
model-index:
|
| 11 |
+
- name: wav2vec2-common_voice-hi-mms-demo
|
| 12 |
+
results:
|
| 13 |
+
- task:
|
| 14 |
+
name: Automatic Speech Recognition
|
| 15 |
+
type: automatic-speech-recognition
|
| 16 |
+
dataset:
|
| 17 |
+
name: common_voice_16_0
|
| 18 |
+
type: common_voice_16_0
|
| 19 |
+
config: hi
|
| 20 |
+
split: test
|
| 21 |
+
args: hi
|
| 22 |
+
metrics:
|
| 23 |
+
- name: Wer
|
| 24 |
+
type: wer
|
| 25 |
+
value: 0.2522266734082688
|
| 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-common_voice-hi-mms-demo
|
| 32 |
+
|
| 33 |
+
This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on the common_voice_16_0 dataset.
|
| 34 |
+
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.2673
|
| 36 |
+
- Wer: 0.2522
|
| 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: 8
|
| 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: 4.0
|
| 63 |
+
- mixed_precision_training: Native AMP
|
| 64 |
+
|
| 65 |
+
### Training results
|
| 66 |
+
|
| 67 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 68 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 69 |
+
| No log | 0.11 | 100 | 0.4487 | 0.3565 |
|
| 70 |
+
| No log | 0.23 | 200 | 0.3544 | 0.3317 |
|
| 71 |
+
| No log | 0.34 | 300 | 0.3693 | 0.3088 |
|
| 72 |
+
| No log | 0.45 | 400 | 0.3404 | 0.3040 |
|
| 73 |
+
| 1.5084 | 0.56 | 500 | 0.3346 | 0.2995 |
|
| 74 |
+
| 1.5084 | 0.68 | 600 | 0.3411 | 0.2936 |
|
| 75 |
+
| 1.5084 | 0.79 | 700 | 0.3175 | 0.2887 |
|
| 76 |
+
| 1.5084 | 0.9 | 800 | 0.3159 | 0.2898 |
|
| 77 |
+
| 1.5084 | 1.02 | 900 | 0.3139 | 0.3045 |
|
| 78 |
+
| 0.3485 | 1.13 | 1000 | 0.3067 | 0.2958 |
|
| 79 |
+
| 0.3485 | 1.24 | 1100 | 0.2969 | 0.2767 |
|
| 80 |
+
| 0.3485 | 1.35 | 1200 | 0.2916 | 0.2714 |
|
| 81 |
+
| 0.3485 | 1.47 | 1300 | 0.2893 | 0.2663 |
|
| 82 |
+
| 0.3485 | 1.58 | 1400 | 0.3183 | 0.2985 |
|
| 83 |
+
| 0.3152 | 1.69 | 1500 | 0.2961 | 0.2688 |
|
| 84 |
+
| 0.3152 | 1.81 | 1600 | 0.2848 | 0.2665 |
|
| 85 |
+
| 0.3152 | 1.92 | 1700 | 0.2844 | 0.2656 |
|
| 86 |
+
| 0.3152 | 2.03 | 1800 | 0.2855 | 0.2707 |
|
| 87 |
+
| 0.3152 | 2.14 | 1900 | 0.2887 | 0.2686 |
|
| 88 |
+
| 0.3058 | 2.26 | 2000 | 0.2858 | 0.2657 |
|
| 89 |
+
| 0.3058 | 2.37 | 2100 | 0.2814 | 0.2629 |
|
| 90 |
+
| 0.3058 | 2.48 | 2200 | 0.2809 | 0.2633 |
|
| 91 |
+
| 0.3058 | 2.6 | 2300 | 0.2779 | 0.2613 |
|
| 92 |
+
| 0.3058 | 2.71 | 2400 | 0.2745 | 0.2581 |
|
| 93 |
+
| 0.2861 | 2.82 | 2500 | 0.2769 | 0.2618 |
|
| 94 |
+
| 0.2861 | 2.93 | 2600 | 0.2742 | 0.2576 |
|
| 95 |
+
| 0.2861 | 3.05 | 2700 | 0.2730 | 0.2575 |
|
| 96 |
+
| 0.2861 | 3.16 | 2800 | 0.2727 | 0.2564 |
|
| 97 |
+
| 0.2861 | 3.27 | 2900 | 0.2726 | 0.2563 |
|
| 98 |
+
| 0.2839 | 3.39 | 3000 | 0.2713 | 0.2576 |
|
| 99 |
+
| 0.2839 | 3.5 | 3100 | 0.2690 | 0.2537 |
|
| 100 |
+
| 0.2839 | 3.61 | 3200 | 0.2706 | 0.2540 |
|
| 101 |
+
| 0.2839 | 3.72 | 3300 | 0.2687 | 0.2542 |
|
| 102 |
+
| 0.2839 | 3.84 | 3400 | 0.2671 | 0.2521 |
|
| 103 |
+
| 0.2706 | 3.95 | 3500 | 0.2673 | 0.2522 |
|
| 104 |
+
|
| 105 |
+
|
| 106 |
+
### Framework versions
|
| 107 |
+
|
| 108 |
+
- Transformers 4.38.0.dev0
|
| 109 |
+
- Pytorch 2.1.2+cu121
|
| 110 |
+
- Datasets 2.16.1
|
| 111 |
+
- Tokenizers 0.15.1
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3859254728
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5485f3c768a6b2603501251cce3ccf582be051de9ecd03aa67598b55259d2821
|
| 3 |
size 3859254728
|