End of training
Browse files- README.md +10 -6
- all_results.json +10 -10
- eval_results.json +6 -6
- train_results.json +4 -4
- trainer_state.json +7 -7
README.md
CHANGED
@@ -1,6 +1,10 @@
|
|
1 |
---
|
|
|
|
|
2 |
license: apache-2.0
|
3 |
tags:
|
|
|
|
|
4 |
- generated_from_trainer
|
5 |
datasets:
|
6 |
- common_voice_13_0
|
@@ -13,15 +17,15 @@ model-index:
|
|
13 |
name: Automatic Speech Recognition
|
14 |
type: automatic-speech-recognition
|
15 |
dataset:
|
16 |
-
name:
|
17 |
type: common_voice_13_0
|
18 |
config: eo
|
19 |
split: validation
|
20 |
-
args: eo
|
21 |
metrics:
|
22 |
- name: Wer
|
23 |
type: wer
|
24 |
-
value: 0.
|
25 |
---
|
26 |
|
27 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -29,11 +33,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
29 |
|
30 |
# wav2vec2-common_voice_13_0-eo-10
|
31 |
|
32 |
-
This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the
|
33 |
It achieves the following results on the evaluation set:
|
34 |
-
- Cer: 0.0119
|
35 |
- Loss: 0.0454
|
36 |
-
-
|
|
|
37 |
|
38 |
## Model description
|
39 |
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
+
- eo
|
4 |
license: apache-2.0
|
5 |
tags:
|
6 |
+
- automatic-speech-recognition
|
7 |
+
- mozilla-foundation/common_voice_13_0
|
8 |
- generated_from_trainer
|
9 |
datasets:
|
10 |
- common_voice_13_0
|
|
|
17 |
name: Automatic Speech Recognition
|
18 |
type: automatic-speech-recognition
|
19 |
dataset:
|
20 |
+
name: MOZILLA-FOUNDATION/COMMON_VOICE_13_0 - EO
|
21 |
type: common_voice_13_0
|
22 |
config: eo
|
23 |
split: validation
|
24 |
+
args: 'Config: eo, Training split: train, Eval split: validation'
|
25 |
metrics:
|
26 |
- name: Wer
|
27 |
type: wer
|
28 |
+
value: 0.06566915357190017
|
29 |
---
|
30 |
|
31 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
33 |
|
34 |
# wav2vec2-common_voice_13_0-eo-10
|
35 |
|
36 |
+
This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the MOZILLA-FOUNDATION/COMMON_VOICE_13_0 - EO dataset.
|
37 |
It achieves the following results on the evaluation set:
|
|
|
38 |
- Loss: 0.0454
|
39 |
+
- Cer: 0.0118
|
40 |
+
- Wer: 0.0657
|
41 |
|
42 |
## Model description
|
43 |
|
all_results.json
CHANGED
@@ -1,15 +1,15 @@
|
|
1 |
{
|
2 |
"epoch": 5.0,
|
3 |
-
"eval_cer": 0.
|
4 |
-
"eval_loss": 0.
|
5 |
-
"eval_runtime":
|
6 |
"eval_samples": 14892,
|
7 |
-
"eval_samples_per_second": 11.
|
8 |
-
"eval_steps_per_second": 1.
|
9 |
-
"eval_wer": 0.
|
10 |
-
"train_loss": 0.
|
11 |
-
"train_runtime":
|
12 |
"train_samples": 143849,
|
13 |
-
"train_samples_per_second":
|
14 |
-
"train_steps_per_second":
|
15 |
}
|
|
|
1 |
{
|
2 |
"epoch": 5.0,
|
3 |
+
"eval_cer": 0.0118367415598033,
|
4 |
+
"eval_loss": 0.045377228409051895,
|
5 |
+
"eval_runtime": 1305.2819,
|
6 |
"eval_samples": 14892,
|
7 |
+
"eval_samples_per_second": 11.409,
|
8 |
+
"eval_steps_per_second": 1.427,
|
9 |
+
"eval_wer": 0.06566915357190017,
|
10 |
+
"train_loss": 0.0023267049651522526,
|
11 |
+
"train_runtime": 2078.5155,
|
12 |
"train_samples": 143849,
|
13 |
+
"train_samples_per_second": 346.038,
|
14 |
+
"train_steps_per_second": 10.813
|
15 |
}
|
eval_results.json
CHANGED
@@ -1,10 +1,10 @@
|
|
1 |
{
|
2 |
"epoch": 5.0,
|
3 |
-
"eval_cer": 0.
|
4 |
-
"eval_loss": 0.
|
5 |
-
"eval_runtime":
|
6 |
"eval_samples": 14892,
|
7 |
-
"eval_samples_per_second": 11.
|
8 |
-
"eval_steps_per_second": 1.
|
9 |
-
"eval_wer": 0.
|
10 |
}
|
|
|
1 |
{
|
2 |
"epoch": 5.0,
|
3 |
+
"eval_cer": 0.0118367415598033,
|
4 |
+
"eval_loss": 0.045377228409051895,
|
5 |
+
"eval_runtime": 1305.2819,
|
6 |
"eval_samples": 14892,
|
7 |
+
"eval_samples_per_second": 11.409,
|
8 |
+
"eval_steps_per_second": 1.427,
|
9 |
+
"eval_wer": 0.06566915357190017
|
10 |
}
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 5.0,
|
3 |
-
"train_loss": 0.
|
4 |
-
"train_runtime":
|
5 |
"train_samples": 143849,
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second":
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 5.0,
|
3 |
+
"train_loss": 0.0023267049651522526,
|
4 |
+
"train_runtime": 2078.5155,
|
5 |
"train_samples": 143849,
|
6 |
+
"train_samples_per_second": 346.038,
|
7 |
+
"train_steps_per_second": 10.813
|
8 |
}
|
trainer_state.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 4.
|
5 |
"global_step": 22475,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
@@ -494,16 +494,16 @@
|
|
494 |
{
|
495 |
"epoch": 5.0,
|
496 |
"step": 22475,
|
497 |
-
"total_flos": 1.
|
498 |
-
"train_loss": 0.
|
499 |
-
"train_runtime":
|
500 |
-
"train_samples_per_second":
|
501 |
-
"train_steps_per_second":
|
502 |
}
|
503 |
],
|
504 |
"max_steps": 22475,
|
505 |
"num_train_epochs": 5,
|
506 |
-
"total_flos": 1.
|
507 |
"trial_name": null,
|
508 |
"trial_params": null
|
509 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.9998887776665555,
|
5 |
"global_step": 22475,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
|
|
494 |
{
|
495 |
"epoch": 5.0,
|
496 |
"step": 22475,
|
497 |
+
"total_flos": 1.360184451953694e+20,
|
498 |
+
"train_loss": 0.0023267049651522526,
|
499 |
+
"train_runtime": 2078.5155,
|
500 |
+
"train_samples_per_second": 346.038,
|
501 |
+
"train_steps_per_second": 10.813
|
502 |
}
|
503 |
],
|
504 |
"max_steps": 22475,
|
505 |
"num_train_epochs": 5,
|
506 |
+
"total_flos": 1.360184451953694e+20,
|
507 |
"trial_name": null,
|
508 |
"trial_params": null
|
509 |
}
|