Model save
Browse files- README.md +88 -0
- run.ami.log +14 -0
README.md
ADDED
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: facebook/wav2vec2-large-lv60
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- ami
|
8 |
+
metrics:
|
9 |
+
- wer
|
10 |
+
model-index:
|
11 |
+
- name: facebook/wav2vec2-large-lv60
|
12 |
+
results:
|
13 |
+
- task:
|
14 |
+
name: Automatic Speech Recognition
|
15 |
+
type: automatic-speech-recognition
|
16 |
+
dataset:
|
17 |
+
name: ami
|
18 |
+
type: ami
|
19 |
+
config: ihm
|
20 |
+
split: None
|
21 |
+
args: ihm
|
22 |
+
metrics:
|
23 |
+
- name: Wer
|
24 |
+
type: wer
|
25 |
+
value: 0.8378987185753448
|
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 |
+
# facebook/wav2vec2-large-lv60
|
32 |
+
|
33 |
+
This model is a fine-tuned version of [facebook/wav2vec2-large-lv60](https://huggingface.co/facebook/wav2vec2-large-lv60) on the ami dataset.
|
34 |
+
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 0.9465
|
36 |
+
- Wer: 0.8379
|
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: 0.0003
|
56 |
+
- train_batch_size: 16
|
57 |
+
- eval_batch_size: 16
|
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: 500
|
62 |
+
- num_epochs: 2.0
|
63 |
+
- mixed_precision_training: Native AMP
|
64 |
+
|
65 |
+
### Training results
|
66 |
+
|
67 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
68 |
+
|:-------------:|:------:|:-----:|:---------------:|:------:|
|
69 |
+
| 1.0919 | 0.1565 | 1000 | 1.0169 | 0.7064 |
|
70 |
+
| 1.4768 | 0.3131 | 2000 | 0.7156 | 0.4356 |
|
71 |
+
| 0.9728 | 0.4696 | 3000 | 0.6462 | 0.4030 |
|
72 |
+
| 0.5418 | 0.6262 | 4000 | 0.6171 | 0.3707 |
|
73 |
+
| 0.8492 | 0.7827 | 5000 | 0.5758 | 0.3695 |
|
74 |
+
| 1.4826 | 0.9393 | 6000 | 0.5801 | 0.3545 |
|
75 |
+
| 0.3274 | 1.0958 | 7000 | 0.5244 | 0.3375 |
|
76 |
+
| 0.2089 | 1.2523 | 8000 | 0.5047 | 0.3239 |
|
77 |
+
| 0.2916 | 1.4089 | 9000 | 0.4901 | 0.3171 |
|
78 |
+
| 0.1617 | 1.5654 | 10000 | 0.5070 | 0.3151 |
|
79 |
+
| 0.3815 | 1.7220 | 11000 | 0.4948 | 0.3180 |
|
80 |
+
| 1.0171 | 1.8785 | 12000 | 0.9465 | 0.8379 |
|
81 |
+
|
82 |
+
|
83 |
+
### Framework versions
|
84 |
+
|
85 |
+
- Transformers 4.42.0.dev0
|
86 |
+
- Pytorch 2.3.0a0+gitcd033a1
|
87 |
+
- Datasets 2.19.1
|
88 |
+
- Tokenizers 0.19.1
|
run.ami.log
CHANGED
@@ -23036,3 +23036,17 @@ Training completed. Do not forget to share your model on huggingface.co/models =
|
|
23036 |
{'loss': 1.2623, 'grad_norm': 4.058191299438477, 'learning_rate': 4.3988269794721406e-07, 'epoch': 2.0}
|
23037 |
|
23038 |
Waiting for the current checkpoint push to be finished, this might take a couple of minutes.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
23036 |
{'loss': 1.2623, 'grad_norm': 4.058191299438477, 'learning_rate': 4.3988269794721406e-07, 'epoch': 2.0}
|
23037 |
|
23038 |
Waiting for the current checkpoint push to be finished, this might take a couple of minutes.
|
23039 |
+
Saving model checkpoint to ./
|
23040 |
+
Configuration saved in ./config.json
|
23041 |
+
Model weights saved in ./model.safetensors
|
23042 |
+
Feature extractor saved in ./preprocessor_config.json
|
23043 |
+
tokenizer config file saved in ./tokenizer_config.json
|
23044 |
+
Special tokens file saved in ./special_tokens_map.json
|
23045 |
+
added tokens file saved in ./added_tokens.json
|
23046 |
+
Saving model checkpoint to ./
|
23047 |
+
Configuration saved in ./config.json
|
23048 |
+
Model weights saved in ./model.safetensors
|
23049 |
+
Feature extractor saved in ./preprocessor_config.json
|
23050 |
+
tokenizer config file saved in ./tokenizer_config.json
|
23051 |
+
Special tokens file saved in ./special_tokens_map.json
|
23052 |
+
added tokens file saved in ./added_tokens.json
|