End of training
Browse files- README.md +16 -29
- adapter_config.json +2 -4
- adapter_model.bin +2 -2
- preprocessor_config.json +1 -1
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -2,24 +2,29 @@
|
|
| 2 |
language:
|
| 3 |
- dj
|
| 4 |
license: apache-2.0
|
| 5 |
-
base_model: openai/whisper-
|
| 6 |
tags:
|
| 7 |
- generated_from_trainer
|
| 8 |
datasets:
|
| 9 |
-
-
|
| 10 |
model-index:
|
| 11 |
-
- name: Whisper
|
| 12 |
results: []
|
| 13 |
---
|
| 14 |
|
| 15 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 16 |
should probably proofread and complete it, then remove this comment. -->
|
| 17 |
|
| 18 |
-
# Whisper
|
| 19 |
|
| 20 |
-
This model is a fine-tuned version of [openai/whisper-
|
| 21 |
It achieves the following results on the evaluation set:
|
| 22 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
|
@@ -38,37 +43,19 @@ More information needed
|
|
| 38 |
### Training hyperparameters
|
| 39 |
|
| 40 |
The following hyperparameters were used during training:
|
| 41 |
-
- learning_rate: 0.
|
| 42 |
- train_batch_size: 8
|
| 43 |
- eval_batch_size: 8
|
| 44 |
- seed: 42
|
| 45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
-
- lr_scheduler_type:
|
| 47 |
-
- lr_scheduler_warmup_steps:
|
| 48 |
-
- num_epochs:
|
| 49 |
- mixed_precision_training: Native AMP
|
| 50 |
|
| 51 |
-
### Training results
|
| 52 |
-
|
| 53 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
| 54 |
-
|:-------------:|:------:|:----:|:---------------:|
|
| 55 |
-
| 1.4992 | 0.2415 | 100 | 1.2243 |
|
| 56 |
-
| 0.8767 | 0.4831 | 200 | 1.6230 |
|
| 57 |
-
| 0.7651 | 0.7246 | 300 | 1.5771 |
|
| 58 |
-
| 0.8255 | 0.9662 | 400 | 2.2942 |
|
| 59 |
-
| 1.0079 | 1.2077 | 500 | 1.5600 |
|
| 60 |
-
| 1.6485 | 1.4493 | 600 | 3.9792 |
|
| 61 |
-
| 1.9125 | 1.6908 | 700 | 4.1289 |
|
| 62 |
-
| 1.2813 | 1.9324 | 800 | 4.8182 |
|
| 63 |
-
| 0.8415 | 2.1739 | 900 | 4.9184 |
|
| 64 |
-
| 0.6234 | 2.4155 | 1000 | 5.0654 |
|
| 65 |
-
| 0.5348 | 2.6570 | 1100 | 5.2614 |
|
| 66 |
-
| 0.4577 | 2.8986 | 1200 | 5.4036 |
|
| 67 |
-
|
| 68 |
-
|
| 69 |
### Framework versions
|
| 70 |
|
| 71 |
-
- Transformers 4.
|
| 72 |
- Pytorch 2.2.1+cu121
|
| 73 |
- Datasets 2.20.0
|
| 74 |
- Tokenizers 0.19.1
|
|
|
|
| 2 |
language:
|
| 3 |
- dj
|
| 4 |
license: apache-2.0
|
| 5 |
+
base_model: openai/whisper-small
|
| 6 |
tags:
|
| 7 |
- generated_from_trainer
|
| 8 |
datasets:
|
| 9 |
+
- fahd1199/datasetdarijatest
|
| 10 |
model-index:
|
| 11 |
+
- name: Whisper Small Darija
|
| 12 |
results: []
|
| 13 |
---
|
| 14 |
|
| 15 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 16 |
should probably proofread and complete it, then remove this comment. -->
|
| 17 |
|
| 18 |
+
# Whisper Small Darija
|
| 19 |
|
| 20 |
+
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the DatasetDarijaTest dataset.
|
| 21 |
It achieves the following results on the evaluation set:
|
| 22 |
+
- eval_loss: 0.7074
|
| 23 |
+
- eval_runtime: 57.1463
|
| 24 |
+
- eval_samples_per_second: 2.625
|
| 25 |
+
- eval_steps_per_second: 0.332
|
| 26 |
+
- epoch: 1.9324
|
| 27 |
+
- step: 800
|
| 28 |
|
| 29 |
## Model description
|
| 30 |
|
|
|
|
| 43 |
### Training hyperparameters
|
| 44 |
|
| 45 |
The following hyperparameters were used during training:
|
| 46 |
+
- learning_rate: 0.0001
|
| 47 |
- train_batch_size: 8
|
| 48 |
- eval_batch_size: 8
|
| 49 |
- seed: 42
|
| 50 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 51 |
+
- lr_scheduler_type: cosine_with_restarts
|
| 52 |
+
- lr_scheduler_warmup_steps: 200
|
| 53 |
+
- num_epochs: 2
|
| 54 |
- mixed_precision_training: Native AMP
|
| 55 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 56 |
### Framework versions
|
| 57 |
|
| 58 |
+
- Transformers 4.44.0
|
| 59 |
- Pytorch 2.2.1+cu121
|
| 60 |
- Datasets 2.20.0
|
| 61 |
- Tokenizers 0.19.1
|
adapter_config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"base_model_name_or_path": "openai/whisper-
|
| 3 |
"bias": "none",
|
| 4 |
"fan_in_fan_out": false,
|
| 5 |
"inference_mode": true,
|
|
@@ -13,9 +13,7 @@
|
|
| 13 |
"q_proj",
|
| 14 |
"v_proj",
|
| 15 |
"k_proj",
|
| 16 |
-
"out_proj"
|
| 17 |
-
"fc1",
|
| 18 |
-
"fc2"
|
| 19 |
],
|
| 20 |
"task_type": null
|
| 21 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"base_model_name_or_path": "openai/whisper-large-v3",
|
| 3 |
"bias": "none",
|
| 4 |
"fan_in_fan_out": false,
|
| 5 |
"inference_mode": true,
|
|
|
|
| 13 |
"q_proj",
|
| 14 |
"v_proj",
|
| 15 |
"k_proj",
|
| 16 |
+
"out_proj"
|
|
|
|
|
|
|
| 17 |
],
|
| 18 |
"task_type": null
|
| 19 |
}
|
adapter_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fe64dd9eae20dc396b4f7d2a123a56a37f263a1ee75a027dbc2d46e3e60cd19f
|
| 3 |
+
size 126113802
|
preprocessor_config.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"chunk_length": 30,
|
| 3 |
"feature_extractor_type": "WhisperFeatureExtractor",
|
| 4 |
-
"feature_size":
|
| 5 |
"hop_length": 160,
|
| 6 |
"n_fft": 400,
|
| 7 |
"n_samples": 480000,
|
|
|
|
| 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,
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5304
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f4e3eac49ae7bfae7d06533090373e54f8bb025e7bffd92059bc3d74f9c51020
|
| 3 |
size 5304
|