Model save
Browse files- README.md +86 -0
- breeze-listen-w2v2-ml.log +2 -0
- model.safetensors +1 -1
README.md
ADDED
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: breeze-listen-w2v2-ml
|
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: ml
|
20 |
+
split: test
|
21 |
+
args: ml
|
22 |
+
metrics:
|
23 |
+
- name: Wer
|
24 |
+
type: wer
|
25 |
+
value: 0.5345542501727713
|
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 |
+
# breeze-listen-w2v2-ml
|
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: 0.2698
|
36 |
+
- Wer: 0.5346
|
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: 4
|
57 |
+
- eval_batch_size: 8
|
58 |
+
- seed: 42
|
59 |
+
- distributed_type: multi-GPU
|
60 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
61 |
+
- lr_scheduler_type: linear
|
62 |
+
- lr_scheduler_warmup_steps: 100
|
63 |
+
- num_epochs: 4.0
|
64 |
+
- mixed_precision_training: Native AMP
|
65 |
+
|
66 |
+
### Training results
|
67 |
+
|
68 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
69 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
70 |
+
| No log | 0.41 | 200 | 5.4728 | 1.0757 |
|
71 |
+
| No log | 0.81 | 400 | 5.1274 | 1.0038 |
|
72 |
+
| 6.5037 | 1.22 | 600 | 0.6167 | 0.8131 |
|
73 |
+
| 6.5037 | 1.63 | 800 | 0.3284 | 0.5829 |
|
74 |
+
| 1.0482 | 2.03 | 1000 | 0.3169 | 0.5667 |
|
75 |
+
| 1.0482 | 2.44 | 1200 | 0.2876 | 0.5425 |
|
76 |
+
| 1.0482 | 2.85 | 1400 | 0.2847 | 0.5522 |
|
77 |
+
| 0.4314 | 3.25 | 1600 | 0.2746 | 0.5394 |
|
78 |
+
| 0.4314 | 3.66 | 1800 | 0.2698 | 0.5346 |
|
79 |
+
|
80 |
+
|
81 |
+
### Framework versions
|
82 |
+
|
83 |
+
- Transformers 4.38.0.dev0
|
84 |
+
- Pytorch 2.1.2+cu121
|
85 |
+
- Datasets 2.16.1
|
86 |
+
- Tokenizers 0.15.1
|
breeze-listen-w2v2-ml.log
CHANGED
@@ -130,3 +130,5 @@ weight_decay=0.0,
|
|
130 |
{'eval_loss': 0.2846720516681671, 'eval_wer': 0.5521769177608846, 'eval_runtime': 161.8788, 'eval_samples_per_second': 4.096, 'eval_steps_per_second': 0.513, 'epoch': 2.85}
|
131 |
{'loss': 0.4314, 'learning_rate': 0.00025374732334047106, 'epoch': 3.05}
|
132 |
{'eval_loss': 0.27460750937461853, 'eval_wer': 0.5393918451969593, 'eval_runtime': 160.7333, 'eval_samples_per_second': 4.125, 'eval_steps_per_second': 0.516, 'epoch': 3.25}
|
|
|
|
|
|
130 |
{'eval_loss': 0.2846720516681671, 'eval_wer': 0.5521769177608846, 'eval_runtime': 161.8788, 'eval_samples_per_second': 4.096, 'eval_steps_per_second': 0.513, 'epoch': 2.85}
|
131 |
{'loss': 0.4314, 'learning_rate': 0.00025374732334047106, 'epoch': 3.05}
|
132 |
{'eval_loss': 0.27460750937461853, 'eval_wer': 0.5393918451969593, 'eval_runtime': 160.7333, 'eval_samples_per_second': 4.125, 'eval_steps_per_second': 0.516, 'epoch': 3.25}
|
133 |
+
{'eval_loss': 0.26981213688850403, 'eval_wer': 0.5345542501727713, 'eval_runtime': 160.1257, 'eval_samples_per_second': 4.14, 'eval_steps_per_second': 0.518, 'epoch': 3.66}
|
134 |
+
{'train_runtime': 5112.0325, 'train_samples_per_second': 1.54, 'train_steps_per_second': 0.385, 'train_loss': 2.1205503649827913, 'epoch': 4.0}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3859111256
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:76cf845e507e18762423f2f1ac9f73ae93f00510cfb7e053bbf30cfe576176af
|
3 |
size 3859111256
|