End of training
Browse files- README.md +4 -28
- config.json +1 -1
- model.safetensors +1 -1
- runs/Mar29_09-57-24_6f4b9df813de/events.out.tfevents.1711706264.6f4b9df813de.26170.1 +3 -0
- training_args.bin +1 -1
README.md
CHANGED
@@ -1,28 +1,13 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
|
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
datasets:
|
6 |
-
-
|
7 |
-
metrics:
|
8 |
-
- wer
|
9 |
-
base_model: facebook/wav2vec2-base-960h
|
10 |
model-index:
|
11 |
- name: wav2vec2-base-fleurs-329-colab-a100-2
|
12 |
-
results:
|
13 |
-
- task:
|
14 |
-
type: automatic-speech-recognition
|
15 |
-
name: Automatic Speech Recognition
|
16 |
-
dataset:
|
17 |
-
name: fleurs
|
18 |
-
type: fleurs
|
19 |
-
config: en_us
|
20 |
-
split: test
|
21 |
-
args: en_us
|
22 |
-
metrics:
|
23 |
-
- type: wer
|
24 |
-
value: 0.9917617237008872
|
25 |
-
name: Wer
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -30,10 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
30 |
|
31 |
# wav2vec2-base-fleurs-329-colab-a100-2
|
32 |
|
33 |
-
This model is a fine-tuned version of [facebook/wav2vec2-base-960h](https://huggingface.co/facebook/wav2vec2-base-960h) on the
|
34 |
-
It achieves the following results on the evaluation set:
|
35 |
-
- Loss: 2.5431
|
36 |
-
- Wer: 0.9918
|
37 |
|
38 |
## Model description
|
39 |
|
@@ -66,12 +48,6 @@ The following hyperparameters were used during training:
|
|
66 |
|
67 |
### Training results
|
68 |
|
69 |
-
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
70 |
-
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
71 |
-
| 8.5696 | 2.45 | 200 | 5.0490 | 1.0 |
|
72 |
-
| 4.0587 | 4.91 | 400 | 3.3808 | 1.0 |
|
73 |
-
| 3.0272 | 7.36 | 600 | 2.7368 | 0.9954 |
|
74 |
-
| 2.6659 | 9.82 | 800 | 2.5431 | 0.9918 |
|
75 |
|
76 |
|
77 |
### Framework versions
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
base_model: facebook/wav2vec2-base-960h
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
7 |
+
- audiofolder
|
|
|
|
|
|
|
8 |
model-index:
|
9 |
- name: wav2vec2-base-fleurs-329-colab-a100-2
|
10 |
+
results: []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
---
|
12 |
|
13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
15 |
|
16 |
# wav2vec2-base-fleurs-329-colab-a100-2
|
17 |
|
18 |
+
This model is a fine-tuned version of [facebook/wav2vec2-base-960h](https://huggingface.co/facebook/wav2vec2-base-960h) on the audiofolder dataset.
|
|
|
|
|
|
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
48 |
|
49 |
### Training results
|
50 |
|
|
|
|
|
|
|
|
|
|
|
|
|
51 |
|
52 |
|
53 |
### Framework versions
|
config.json
CHANGED
@@ -79,7 +79,7 @@
|
|
79 |
"num_hidden_layers": 12,
|
80 |
"num_negatives": 100,
|
81 |
"output_hidden_size": 768,
|
82 |
-
"pad_token_id":
|
83 |
"proj_codevector_dim": 256,
|
84 |
"tdnn_dilation": [
|
85 |
1,
|
|
|
79 |
"num_hidden_layers": 12,
|
80 |
"num_negatives": 100,
|
81 |
"output_hidden_size": 768,
|
82 |
+
"pad_token_id": 27,
|
83 |
"proj_codevector_dim": 256,
|
84 |
"tdnn_dilation": [
|
85 |
1,
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 377611120
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d1e9f6b83e3e1b76e0b3520638e1600e5fa36db60a03694885f65d36da3997e9
|
3 |
size 377611120
|
runs/Mar29_09-57-24_6f4b9df813de/events.out.tfevents.1711706264.6f4b9df813de.26170.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:60ef4594042dff5cb9cb6aa48ce0841209a120b4ab5e968b49a01c3d11db3cd8
|
3 |
+
size 6415
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a4ee4434a100159ef3ea972154a0ed02baf5bc65cce2577c7eb8741298978455
|
3 |
size 4920
|