update model card README.md
Browse files
README.md
CHANGED
@@ -1,16 +1,11 @@
|
|
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
|
11 |
metrics:
|
12 |
- wer
|
13 |
-
- cer
|
14 |
model-index:
|
15 |
- name: wav2vec2-common_voice_13_0-eo-10
|
16 |
results:
|
@@ -18,68 +13,42 @@ model-index:
|
|
18 |
name: Automatic Speech Recognition
|
19 |
type: automatic-speech-recognition
|
20 |
dataset:
|
21 |
-
name:
|
22 |
type: common_voice_13_0
|
23 |
config: eo
|
24 |
split: validation
|
25 |
-
args:
|
26 |
metrics:
|
27 |
-
- name:
|
28 |
type: wer
|
29 |
-
value: 0.
|
30 |
-
- name: CER
|
31 |
-
type: cer
|
32 |
-
value: 0.0118
|
33 |
---
|
34 |
|
35 |
-
|
|
|
36 |
|
37 |
-
|
|
|
|
|
38 |
It achieves the following results on the evaluation set:
|
39 |
-
-
|
40 |
-
-
|
41 |
-
- Wer: 0.
|
42 |
-
|
43 |
-
The first 10 examples in the evaluation set:
|
44 |
-
|
45 |
-
| Actual<br>Predicted | CER |
|
46 |
-
|:--------------------|:----|
|
47 |
-
| `la orienta parto apud benino kaj niĝerio estis nomita sklavmarbordo`<br>`la orienta parto apud benino kaj niĝerio estis nomita sklafmarbordo` | 0.014925373134328358 |
|
48 |
-
| `en la sekva jaro li ricevis premion`<br>`en la sekva jaro li ricevis premion` | 0.0 |
|
49 |
-
| `ŝi studis historion ĉe la universitato de brita kolumbio`<br>`ŝi studis historion ĉe la universitato de brita kolumbio` | 0.0 |
|
50 |
-
| `larĝaj ŝtupoj kuras al la fasado`<br>`larĝaj ŝtupoj kuras al la fasado` | 0.0 |
|
51 |
-
| `la municipo ĝuas duan epokon de etendo kaj disvolviĝo`<br>`la municipo ĝuas duan eepokon de etendo kaj disvolviĝo` | 0.018867924528301886 |
|
52 |
-
| `li estis ankaŭ katedrestro kaj dekano`<br>`li estis ankaŭ katedristo kaj dekano` | 0.05405405405405406 |
|
53 |
-
| `librovendejo apartenas al la muzeo`<br>`librovendejo apartenas al la muzeo` | 0.0 |
|
54 |
-
| `ĝi estas kutime malfacile videbla kaj troviĝas en subkreskaĵaro de arbaroj`<br>`ĝi estas kutime malfacile videbla kaj troviĝas en subkreskaĵo de arbaroj` | 0.02702702702702703 |
|
55 |
-
| `unue ili estas ruĝaj poste brunaj`<br>`unue ili estas ruĝaj poste brunaj` | 0.0 |
|
56 |
-
| `la loĝantaro laboras en la proksima ĉefurbo`<br>`la loĝantaro laboras en la proksima ĉefurbo` | 0.0 |
|
57 |
|
58 |
## Model description
|
59 |
|
60 |
-
|
61 |
|
62 |
## Intended uses & limitations
|
63 |
|
64 |
-
|
65 |
-
|
66 |
-
The output is all lowercase, no punctuation.
|
67 |
|
68 |
## Training and evaluation data
|
69 |
|
70 |
-
|
71 |
|
72 |
## Training procedure
|
73 |
|
74 |
-
I used a modified version of [`run_speech_recognition_ctc.py`](https://github.com/huggingface/transformers/tree/main/examples/pytorch/speech-recognition) for training. See [`run_speech_recognition_ctc.py`](https://huggingface.co/xekri/wav2vec2-common_voice_13_0-eo-10/blob/main/run_speech_recognition_ctc.py) in this repo.
|
75 |
-
|
76 |
-
The parameters to the trainer are in [train.json](https://huggingface.co/xekri/wav2vec2-common_voice_13_0-eo-10/blob/main/train.json) in this repo.
|
77 |
-
|
78 |
-
The key changes between this training run and `xekri/wav2vec2-common_voice_13_0-eo-3`, aside from the filtering and use of the full training and validation sets are:
|
79 |
-
|
80 |
-
* Layer drop probability is 20%
|
81 |
-
* Train only for 5 epochs
|
82 |
-
|
83 |
### Training hyperparameters
|
84 |
|
85 |
The following hyperparameters were used during training:
|
@@ -89,7 +58,6 @@ The following hyperparameters were used during training:
|
|
89 |
- seed: 42
|
90 |
- gradient_accumulation_steps: 2
|
91 |
- total_train_batch_size: 32
|
92 |
-
- layerdrop: 0.2
|
93 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
94 |
- lr_scheduler_type: linear
|
95 |
- lr_scheduler_warmup_steps: 500
|
|
|
1 |
---
|
|
|
|
|
2 |
license: apache-2.0
|
3 |
tags:
|
|
|
|
|
4 |
- generated_from_trainer
|
5 |
datasets:
|
6 |
- common_voice_13_0
|
7 |
metrics:
|
8 |
- wer
|
|
|
9 |
model-index:
|
10 |
- name: wav2vec2-common_voice_13_0-eo-10
|
11 |
results:
|
|
|
13 |
name: Automatic Speech Recognition
|
14 |
type: automatic-speech-recognition
|
15 |
dataset:
|
16 |
+
name: common_voice_13_0
|
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: 0.06575168361283507
|
|
|
|
|
|
|
25 |
---
|
26 |
|
27 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
28 |
+
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 common_voice_13_0 dataset.
|
33 |
It achieves the following results on the evaluation set:
|
34 |
+
- Cer: 0.0119
|
35 |
+
- Loss: 0.0454
|
36 |
+
- Wer: 0.0658
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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:
|
|
|
58 |
- seed: 42
|
59 |
- gradient_accumulation_steps: 2
|
60 |
- total_train_batch_size: 32
|
|
|
61 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
62 |
- lr_scheduler_type: linear
|
63 |
- lr_scheduler_warmup_steps: 500
|