kavyamanohar
commited on
Commit
•
8fe548d
1
Parent(s):
d8e98ab
Update README.md
Browse files
README.md
CHANGED
@@ -8,6 +8,14 @@ metrics:
|
|
8 |
model-index:
|
9 |
- name: w2v-bert-studio
|
10 |
results: []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
---
|
12 |
|
13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -15,7 +23,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
# w2v-bert-studio
|
17 |
|
18 |
-
This model is a fine-tuned version of [facebook/w2v-bert-2.0](https://huggingface.co/facebook/w2v-bert-2.0) on
|
19 |
It achieves the following results on the evaluation set:
|
20 |
- Loss: 0.1587
|
21 |
- Wer: 0.1157
|
@@ -80,4 +88,4 @@ The following hyperparameters were used during training:
|
|
80 |
- Transformers 4.42.2
|
81 |
- Pytorch 2.1.1+cu121
|
82 |
- Datasets 2.20.0
|
83 |
-
- Tokenizers 0.19.1
|
|
|
8 |
model-index:
|
9 |
- name: w2v-bert-studio
|
10 |
results: []
|
11 |
+
datasets:
|
12 |
+
- thennal/IMaSC
|
13 |
+
- vrclc/festvox-iiith-ml
|
14 |
+
- vrclc/openslr63
|
15 |
+
language:
|
16 |
+
- ml
|
17 |
+
library_name: transformers
|
18 |
+
pipeline_tag: text-generation
|
19 |
---
|
20 |
|
21 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
23 |
|
24 |
# w2v-bert-studio
|
25 |
|
26 |
+
This model is a fine-tuned version of [facebook/w2v-bert-2.0](https://huggingface.co/facebook/w2v-bert-2.0) on [IMASC](https://huggingface.co/datasets/thennal/IMaSC), [OpenSLR Malayalam Train split](https://huggingface.co/datasets/vrclc/openslr63), [Festvox Malayalam](https://huggingface.co/datasets/vrclc/festvox-iiith-ml)dataset.
|
27 |
It achieves the following results on the evaluation set:
|
28 |
- Loss: 0.1587
|
29 |
- Wer: 0.1157
|
|
|
88 |
- Transformers 4.42.2
|
89 |
- Pytorch 2.1.1+cu121
|
90 |
- Datasets 2.20.0
|
91 |
+
- Tokenizers 0.19.1
|