Hugging Face's logo

kiranpantha
/
whisper-large-v3-nepali-lora-ex-1

PEFT
TensorBoard
Safetensors
Nepali
Generated from Trainer
Model card Files Metrics Community
kiranpantha commited on
Commit
d777ab2
·
verified ·
1 Parent(s): 6c026b2

End of training

Browse files
Files changed (9) hide show
  1. README.md +8 -8
  2. adapter_config.json +1 -1
  3. adapter_model.safetensors +1 -1
  4. runs/Jan12_20-49-55_idc-training-gpu-compute-29/events.out.tfevents.1736715016.idc-training-gpu-compute-29.67836.6 +3 -0
  5. runs/Jan12_20-50-53_idc-training-gpu-compute-29/events.out.tfevents.1736715060.idc-training-gpu-compute-29.67836.7 +3 -0
  6. runs/Jan12_20-52-42_idc-training-gpu-compute-29/events.out.tfevents.1736715169.idc-training-gpu-compute-29.67836.8 +3 -0
  7. runs/Jan12_20-55-45_idc-training-gpu-compute-29/events.out.tfevents.1736715345.idc-training-gpu-compute-29.67836.9 +3 -0
  8. runs/Jan12_21-13-38_idc-training-gpu-compute-29/events.out.tfevents.1736716418.idc-training-gpu-compute-29.67836.10 +3 -0
  9. training_args.bin +1 -1
README.md CHANGED
@@ -3,24 +3,24 @@ library_name: peft
3
  language:
4
  - ne
5
  license: apache-2.0
6
- base_model: kiranpantha/whisper-large-v3-nepali
7
  tags:
8
  - generated_from_trainer
9
  datasets:
10
  - kiranpantha/OpenSLR54-Balanced-Nepali
11
  model-index:
12
- - name: kiranpantha/whisper-large-v3-nepali
13
  results: []
14
  ---
15
 
16
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
  should probably proofread and complete it, then remove this comment. -->
18
 
19
- # kiranpantha/whisper-large-v3-nepali
20
 
21
- This model is a fine-tuned version of [kiranpantha/whisper-large-v3-nepali](https://huggingface.co/kiranpantha/whisper-large-v3-nepali) on the OpenSLR54 dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.3071
24
 
25
  ## Model description
26
 
@@ -53,9 +53,9 @@ The following hyperparameters were used during training:
53
 
54
  | Training Loss | Epoch | Step | Validation Loss |
55
  |:-------------:|:-----:|:----:|:---------------:|
56
- | No log | 1.0 | 13 | 0.3046 |
57
- | 0.0396 | 2.0 | 26 | 0.2943 |
58
- | 0.0396 | 3.0 | 39 | 0.3071 |
59
 
60
 
61
  ### Framework versions
 
3
  language:
4
  - ne
5
  license: apache-2.0
6
+ base_model: openai/whisper-large-v3
7
  tags:
8
  - generated_from_trainer
9
  datasets:
10
  - kiranpantha/OpenSLR54-Balanced-Nepali
11
  model-index:
12
+ - name: openai/whisper-large-v3
13
  results: []
14
  ---
15
 
16
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
  should probably proofread and complete it, then remove this comment. -->
18
 
19
+ # openai/whisper-large-v3
20
 
21
+ This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the OpenSLR54 dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.4442
24
 
25
  ## Model description
26
 
 
53
 
54
  | Training Loss | Epoch | Step | Validation Loss |
55
  |:-------------:|:-----:|:----:|:---------------:|
56
+ | No log | 1.0 | 14 | 0.5178 |
57
+ | 0.5309 | 2.0 | 28 | 0.4394 |
58
+ | 0.5309 | 3.0 | 42 | 0.4442 |
59
 
60
 
61
  ### Framework versions
adapter_config.json CHANGED
@@ -4,7 +4,7 @@
4
  "base_model_class": "WhisperForConditionalGeneration",
5
  "parent_library": "transformers.models.whisper.modeling_whisper"
6
  },
7
- "base_model_name_or_path": "kiranpantha/whisper-large-v3-nepali",
8
  "bias": "none",
9
  "eva_config": null,
10
  "exclude_modules": null,
 
4
  "base_model_class": "WhisperForConditionalGeneration",
5
  "parent_library": "transformers.models.whisper.modeling_whisper"
6
  },
7
+ "base_model_name_or_path": "openai/whisper-large-v3",
8
  "bias": "none",
9
  "eva_config": null,
10
  "exclude_modules": null,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2cb3ded99bbe4ca65db29422a92c530cd44c9d5899ed527aa5efe668283a21d7
3
  size 62969640
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e4f198a005172af78b715fc7609c917c17f60779c8d36163b7b1bd91b8a1fc9
3
  size 62969640
runs/Jan12_20-49-55_idc-training-gpu-compute-29/events.out.tfevents.1736715016.idc-training-gpu-compute-29.67836.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecdb39c0d6462a1442c6a905b9d62eb7d70961c656b44cc645b95849dc26c938
3
+ size 5981
runs/Jan12_20-50-53_idc-training-gpu-compute-29/events.out.tfevents.1736715060.idc-training-gpu-compute-29.67836.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9634dc916b64456d03361ccdfc336f9b86d8524e139ae2cbbce3f265442045d9
3
+ size 5982
runs/Jan12_20-52-42_idc-training-gpu-compute-29/events.out.tfevents.1736715169.idc-training-gpu-compute-29.67836.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4ab96cd6b48076aa19299356e380ce8de89dac158a631639518601c9a3ef92d
3
+ size 5981
runs/Jan12_20-55-45_idc-training-gpu-compute-29/events.out.tfevents.1736715345.idc-training-gpu-compute-29.67836.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0e1ef0a56f4b7f5e217a74c141f896af15ae392e3263558ab03cd6982d63c4d
3
+ size 7334
runs/Jan12_21-13-38_idc-training-gpu-compute-29/events.out.tfevents.1736716418.idc-training-gpu-compute-29.67836.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d1f7afd3380d106daef78a20b4afab132c8468319a49292d50729e4d802e55e
3
+ size 7341
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:13a5b934ea675dd40e571e17787f4393f326f6f19193fca3b9be463cd7b80cea
3
  size 5560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afb6496d6069e97a053086ac1d615cca14debadad79e97a4540d7aafec81f60c
3
  size 5560