End of training
Browse files
README.md
CHANGED
@@ -20,8 +20,6 @@ should probably proofread and complete it, then remove this comment. -->
|
|
20 |
# Abhinav28/whisper-large-v3-hindi-100steps
|
21 |
|
22 |
This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the Common Voice 11.0 dataset.
|
23 |
-
It achieves the following results on the evaluation set:
|
24 |
-
- Loss: 0.4629
|
25 |
|
26 |
## Model description
|
27 |
|
@@ -54,7 +52,7 @@ The following hyperparameters were used during training:
|
|
54 |
|
55 |
| Training Loss | Epoch | Step | Validation Loss |
|
56 |
|:-------------:|:-----:|:----:|:---------------:|
|
57 |
-
|
|
58 |
|
59 |
|
60 |
### Framework versions
|
|
|
20 |
# Abhinav28/whisper-large-v3-hindi-100steps
|
21 |
|
22 |
This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the Common Voice 11.0 dataset.
|
|
|
|
|
23 |
|
24 |
## Model description
|
25 |
|
|
|
52 |
|
53 |
| Training Loss | Epoch | Step | Validation Loss |
|
54 |
|:-------------:|:-----:|:----:|:---------------:|
|
55 |
+
| No log | 0.77 | 10 | 0.4666 |
|
56 |
|
57 |
|
58 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -22,8 +22,8 @@
|
|
22 |
"rank_pattern": {},
|
23 |
"revision": null,
|
24 |
"target_modules": [
|
25 |
-
"
|
26 |
-
"
|
27 |
],
|
28 |
"task_type": null,
|
29 |
"use_rslora": false
|
|
|
22 |
"rank_pattern": {},
|
23 |
"revision": null,
|
24 |
"target_modules": [
|
25 |
+
"q_proj",
|
26 |
+
"v_proj"
|
27 |
],
|
28 |
"task_type": null,
|
29 |
"use_rslora": false
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 62969640
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2b66f1b414fe86209cd99b82b512fa0d9da352697fbc0d18c22a716926826dd7
|
3 |
size 62969640
|
runs/Jan05_15-24-37_jupyter-abhinav-2eswami-40telusinternational-2ecom/events.out.tfevents.1704468277.jupyter-abhinav-2eswami-40telusinternational-2ecom.11993.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b34c452f6aa0231aea4f717ddc02a5d5dfde42a0c794a029c57a69d232b19eb1
|
3 |
+
size 6224
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4475
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:498cdfd7afc029e34fd2799a36b5b5890d8af874c5e24a7d7c7e4573983b68b2
|
3 |
size 4475
|