Chahat7874
commited on
Commit
•
cadf363
1
Parent(s):
5b4aacf
Model save
Browse files
README.md
CHANGED
@@ -1,33 +1,13 @@
|
|
1 |
---
|
2 |
-
language:
|
3 |
-
- hi
|
4 |
license: apache-2.0
|
5 |
base_model: facebook/wav2vec2-large-xlsr-53
|
6 |
tags:
|
7 |
-
- automatic-speech-recognition
|
8 |
-
- mozilla-foundation/common_voice_15_0
|
9 |
-
- mms
|
10 |
- generated_from_trainer
|
11 |
datasets:
|
12 |
- common_voice_15_0
|
13 |
-
metrics:
|
14 |
-
- wer
|
15 |
model-index:
|
16 |
- name: wav2vec2-common_voice-en-demo
|
17 |
-
results:
|
18 |
-
- task:
|
19 |
-
name: Automatic Speech Recognition
|
20 |
-
type: automatic-speech-recognition
|
21 |
-
dataset:
|
22 |
-
name: MOZILLA-FOUNDATION/COMMON_VOICE_15_0 - HI
|
23 |
-
type: common_voice_15_0
|
24 |
-
config: hi
|
25 |
-
split: validation
|
26 |
-
args: 'Config: hi, Training split: train, Eval split: validation'
|
27 |
-
metrics:
|
28 |
-
- name: Wer
|
29 |
-
type: wer
|
30 |
-
value: 1.0
|
31 |
---
|
32 |
|
33 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -35,10 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
35 |
|
36 |
# wav2vec2-common_voice-en-demo
|
37 |
|
38 |
-
This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the
|
39 |
-
It achieves the following results on the evaluation set:
|
40 |
-
- Loss: 3.4594
|
41 |
-
- Wer: 1.0
|
42 |
|
43 |
## Model description
|
44 |
|
@@ -66,20 +43,14 @@ The following hyperparameters were used during training:
|
|
66 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
67 |
- lr_scheduler_type: linear
|
68 |
- lr_scheduler_warmup_steps: 500
|
69 |
-
- num_epochs:
|
70 |
- mixed_precision_training: Native AMP
|
71 |
|
72 |
### Training results
|
73 |
|
74 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
75 |
|:-------------:|:------:|:----:|:---------------:|:------:|
|
76 |
-
| No log | 0.6897 | 100 | 21.
|
77 |
-
| No log | 1.3793 | 200 | 17.2935 | 1.0 |
|
78 |
-
| No log | 2.0690 | 300 | 3.5211 | 1.0 |
|
79 |
-
| No log | 2.7586 | 400 | 3.5074 | 1.0 |
|
80 |
-
| 9.5434 | 3.4483 | 500 | 3.4881 | 1.0 |
|
81 |
-
| 9.5434 | 4.1379 | 600 | 3.4876 | 1.0 |
|
82 |
-
| 9.5434 | 4.8276 | 700 | 3.4896 | 1.0 |
|
83 |
|
84 |
|
85 |
### Framework versions
|
|
|
1 |
---
|
|
|
|
|
2 |
license: apache-2.0
|
3 |
base_model: facebook/wav2vec2-large-xlsr-53
|
4 |
tags:
|
|
|
|
|
|
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
7 |
- common_voice_15_0
|
|
|
|
|
8 |
model-index:
|
9 |
- name: wav2vec2-common_voice-en-demo
|
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-common_voice-en-demo
|
17 |
|
18 |
+
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_15_0 dataset.
|
|
|
|
|
|
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
- lr_scheduler_type: linear
|
45 |
- lr_scheduler_warmup_steps: 500
|
46 |
+
- num_epochs: 1.0
|
47 |
- mixed_precision_training: Native AMP
|
48 |
|
49 |
### Training results
|
50 |
|
51 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
52 |
|:-------------:|:------:|:----:|:---------------:|:------:|
|
53 |
+
| No log | 0.6897 | 100 | 21.9479 | 1.0003 |
|
|
|
|
|
|
|
|
|
|
|
|
|
54 |
|
55 |
|
56 |
### Framework versions
|