nomnoos37/stt-turbo-1226-v1.4

README.md

@@ -0,0 +1,112 @@
+---
+library_name: peft
+language:
+- ko
+license: mit
+base_model: openai/whisper-large-v3-turbo
+tags:
+- generated_from_trainer
+model-index:
+- name: Whisper Small ko
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# Whisper Small ko
+
+This model is a fine-tuned version of [openai/whisper-large-v3-turbo](https://huggingface.co/openai/whisper-large-v3-turbo) on the custom dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2388
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 64
+- eval_batch_size: 256
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 50
+- training_steps: 500
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.8865        | 0.0901 | 10   | 1.5498          |
+| 0.8668        | 0.1802 | 20   | 1.4739          |
+| 0.7179        | 0.2703 | 30   | 1.2411          |
+| 0.3916        | 0.3604 | 40   | 0.8666          |
+| 0.219         | 0.4505 | 50   | 0.7558          |
+| 0.1545        | 0.5405 | 60   | 0.6752          |
+| 0.1278        | 0.6306 | 70   | 0.5819          |
+| 0.0983        | 0.7207 | 80   | 0.5394          |
+| 0.0908        | 0.8108 | 90   | 0.5013          |
+| 0.0718        | 0.9009 | 100  | 0.4740          |
+| 0.0773        | 0.9910 | 110  | 0.4579          |
+| 0.0665        | 1.0811 | 120  | 0.4430          |
+| 0.0608        | 1.1712 | 130  | 0.4284          |
+| 0.0612        | 1.2613 | 140  | 0.4136          |
+| 0.0605        | 1.3514 | 150  | 0.4104          |
+| 0.0632        | 1.4414 | 160  | 0.3857          |
+| 0.0534        | 1.5315 | 170  | 0.3678          |
+| 0.0527        | 1.6216 | 180  | 0.3584          |
+| 0.0516        | 1.7117 | 190  | 0.3458          |
+| 0.0467        | 1.8018 | 200  | 0.3373          |
+| 0.0526        | 1.8919 | 210  | 0.3299          |
+| 0.0363        | 1.9820 | 220  | 0.3280          |
+| 0.0468        | 2.0721 | 230  | 0.3202          |
+| 0.0473        | 2.1622 | 240  | 0.3152          |
+| 0.0394        | 2.2523 | 250  | 0.3065          |
+| 0.0356        | 2.3423 | 260  | 0.3009          |
+| 0.042         | 2.4324 | 270  | 0.2934          |
+| 0.042         | 2.5225 | 280  | 0.2911          |
+| 0.0314        | 2.6126 | 290  | 0.2899          |
+| 0.0397        | 2.7027 | 300  | 0.2817          |
+| 0.0377        | 2.7928 | 310  | 0.2743          |
+| 0.0412        | 2.8829 | 320  | 0.2695          |
+| 0.0362        | 2.9730 | 330  | 0.2649          |
+| 0.0321        | 3.0631 | 340  | 0.2589          |
+| 0.0406        | 3.1532 | 350  | 0.2572          |
+| 0.028         | 3.2432 | 360  | 0.2568          |
+| 0.0345        | 3.3333 | 370  | 0.2568          |
+| 0.0346        | 3.4234 | 380  | 0.2544          |
+| 0.0391        | 3.5135 | 390  | 0.2513          |
+| 0.0362        | 3.6036 | 400  | 0.2468          |
+| 0.0304        | 3.6937 | 410  | 0.2446          |
+| 0.032         | 3.7838 | 420  | 0.2428          |
+| 0.0307        | 3.8739 | 430  | 0.2422          |
+| 0.0301        | 3.9640 | 440  | 0.2414          |
+| 0.0315        | 4.0541 | 450  | 0.2396          |
+| 0.0336        | 4.1441 | 460  | 0.2396          |
+| 0.024         | 4.2342 | 470  | 0.2396          |
+| 0.0286        | 4.3243 | 480  | 0.2391          |
+| 0.0289        | 4.4144 | 490  | 0.2389          |
+| 0.0323        | 4.5045 | 500  | 0.2388          |
+
+
+### Framework versions
+
+- PEFT 0.14.0
+- Transformers 4.47.1
+- Pytorch 2.5.1+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.0

adapter_config.json

@@ -0,0 +1,35 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "WhisperForConditionalGeneration",
+    "parent_library": "transformers.models.whisper.modeling_whisper"
+  },
+  "base_model_name_or_path": "openai/whisper-large-v3-turbo",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bcfd4d64b1c5d31b275edd65f2a13831078634f4fcbd763d2f7afb4b3f9664c
+size 26237160

preprocessor_config.json

@@ -0,0 +1,14 @@
+{
+  "chunk_length": 30,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 128,
+  "hop_length": 160,
+  "n_fft": 400,
+  "n_samples": 480000,
+  "nb_max_frames": 3000,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "WhisperProcessor",
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

runs/Dec26_13-08-16_gglabs-a6000/events.out.tfevents.1735236497.gglabs-a6000

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd13a4ce544879c43758cb7a4aecbeb0cd18be759585d445068a5ba23b406833
+size 30665

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31969dfd667372a975003c7d5d17d1cd5baa63e1c12eb9780a895706b3c10434
+size 5496