End of training
Browse files- README.md +75 -0
- adapter_config.json +30 -0
- adapter_model.safetensors +3 -0
- preprocessor_config.json +14 -0
- runs/Jan05_13-32-01_jupyter-abhinav-2eswami-40telusinternational-2ecom/events.out.tfevents.1704461534.jupyter-abhinav-2eswami-40telusinternational-2ecom.899.0 +3 -0
- runs/Jan05_13-32-01_jupyter-abhinav-2eswami-40telusinternational-2ecom/events.out.tfevents.1704461666.jupyter-abhinav-2eswami-40telusinternational-2ecom.899.1 +3 -0
- runs/Jan05_13-47-33_jupyter-abhinav-2eswami-40telusinternational-2ecom/events.out.tfevents.1704462453.jupyter-abhinav-2eswami-40telusinternational-2ecom.11062.0 +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- hi
|
4 |
+
license: apache-2.0
|
5 |
+
library_name: peft
|
6 |
+
tags:
|
7 |
+
- hf-asr-leaderboard
|
8 |
+
- generated_from_trainer
|
9 |
+
datasets:
|
10 |
+
- mozilla-foundation/common_voice_11_0
|
11 |
+
base_model: openai/whisper-large-v3
|
12 |
+
model-index:
|
13 |
+
- name: Abhinav28/whisper-large-v3-hindi-100steps
|
14 |
+
results: []
|
15 |
+
---
|
16 |
+
|
17 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
18 |
+
should probably proofread and complete it, then remove this comment. -->
|
19 |
+
|
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: 0.3031
|
25 |
+
|
26 |
+
## Model description
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Intended uses & limitations
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training and evaluation data
|
35 |
+
|
36 |
+
More information needed
|
37 |
+
|
38 |
+
## Training procedure
|
39 |
+
|
40 |
+
### Training hyperparameters
|
41 |
+
|
42 |
+
The following hyperparameters were used during training:
|
43 |
+
- learning_rate: 0.001
|
44 |
+
- train_batch_size: 8
|
45 |
+
- eval_batch_size: 8
|
46 |
+
- seed: 42
|
47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
48 |
+
- lr_scheduler_type: linear
|
49 |
+
- lr_scheduler_warmup_steps: 50
|
50 |
+
- training_steps: 100
|
51 |
+
- mixed_precision_training: Native AMP
|
52 |
+
|
53 |
+
### Training results
|
54 |
+
|
55 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
56 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
57 |
+
| No log | 0.77 | 10 | 0.7025 |
|
58 |
+
| No log | 1.54 | 20 | 0.4690 |
|
59 |
+
| No log | 2.31 | 30 | 0.3444 |
|
60 |
+
| No log | 3.08 | 40 | 0.2747 |
|
61 |
+
| No log | 3.85 | 50 | 0.3133 |
|
62 |
+
| No log | 4.62 | 60 | 0.3181 |
|
63 |
+
| No log | 5.38 | 70 | 0.3010 |
|
64 |
+
| No log | 6.15 | 80 | 0.2810 |
|
65 |
+
| No log | 6.92 | 90 | 0.3127 |
|
66 |
+
| 0.2416 | 7.69 | 100 | 0.3031 |
|
67 |
+
|
68 |
+
|
69 |
+
### Framework versions
|
70 |
+
|
71 |
+
- PEFT 0.7.2.dev0
|
72 |
+
- Transformers 4.36.2
|
73 |
+
- Pytorch 2.0.0
|
74 |
+
- Datasets 2.16.1
|
75 |
+
- Tokenizers 0.15.0
|
adapter_config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": {
|
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 |
+
"fan_in_fan_out": false,
|
10 |
+
"inference_mode": true,
|
11 |
+
"init_lora_weights": true,
|
12 |
+
"layers_pattern": null,
|
13 |
+
"layers_to_transform": null,
|
14 |
+
"loftq_config": {},
|
15 |
+
"lora_alpha": 64,
|
16 |
+
"lora_dropout": 0.05,
|
17 |
+
"megatron_config": null,
|
18 |
+
"megatron_core": "megatron.core",
|
19 |
+
"modules_to_save": null,
|
20 |
+
"peft_type": "LORA",
|
21 |
+
"r": 32,
|
22 |
+
"rank_pattern": {},
|
23 |
+
"revision": null,
|
24 |
+
"target_modules": [
|
25 |
+
"v_proj",
|
26 |
+
"q_proj"
|
27 |
+
],
|
28 |
+
"task_type": null,
|
29 |
+
"use_rslora": false
|
30 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ab58387c894698c3c0f2b86f22d7260d171a12d5f1ab96513503965abc4e48e3
|
3 |
+
size 62969640
|
preprocessor_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"chunk_length": 30,
|
3 |
+
"feature_extractor_type": "WhisperFeatureExtractor",
|
4 |
+
"feature_size": 128,
|
5 |
+
"hop_length": 160,
|
6 |
+
"n_fft": 400,
|
7 |
+
"n_samples": 480000,
|
8 |
+
"nb_max_frames": 3000,
|
9 |
+
"padding_side": "right",
|
10 |
+
"padding_value": 0.0,
|
11 |
+
"processor_class": "WhisperProcessor",
|
12 |
+
"return_attention_mask": false,
|
13 |
+
"sampling_rate": 16000
|
14 |
+
}
|
runs/Jan05_13-32-01_jupyter-abhinav-2eswami-40telusinternational-2ecom/events.out.tfevents.1704461534.jupyter-abhinav-2eswami-40telusinternational-2ecom.899.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:903c14e665dc1114282283647f16373bc4b2ccb7ac4929a7c783c61e4e42105d
|
3 |
+
size 5612
|
runs/Jan05_13-32-01_jupyter-abhinav-2eswami-40telusinternational-2ecom/events.out.tfevents.1704461666.jupyter-abhinav-2eswami-40telusinternational-2ecom.899.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:db93309d09bec11eeeb487570d26830e349f25d7e198c5c5789b934985128200
|
3 |
+
size 8006
|
runs/Jan05_13-47-33_jupyter-abhinav-2eswami-40telusinternational-2ecom/events.out.tfevents.1704462453.jupyter-abhinav-2eswami-40telusinternational-2ecom.11062.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8708badf3288c2dba56f9a2a10e7132a2dcd485a5681853837b66bf55ad4beb
|
3 |
+
size 8774
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:29e48557e772095dad7172dbc2252c8cf432e0ad0e6d9e70b065fe2fe2aae362
|
3 |
+
size 4475
|