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: 0.1812
+
+## 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 |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.8642        | 0.1449 | 10   | 1.5475          |
+| 0.8061        | 0.2899 | 20   | 1.4627          |
+| 0.6409        | 0.4348 | 30   | 1.2193          |
+| 0.3296        | 0.5797 | 40   | 0.8200          |
+| 0.178         | 0.7246 | 50   | 0.7032          |
+| 0.1336        | 0.8696 | 60   | 0.6138          |
+| 0.1064        | 1.0145 | 70   | 0.5193          |
+| 0.0846        | 1.1594 | 80   | 0.4691          |
+| 0.0728        | 1.3043 | 90   | 0.4360          |
+| 0.0681        | 1.4493 | 100  | 0.4071          |
+| 0.0566        | 1.5942 | 110  | 0.3891          |
+| 0.0613        | 1.7391 | 120  | 0.3695          |
+| 0.0441        | 1.8841 | 130  | 0.3587          |
+| 0.0469        | 2.0290 | 140  | 0.3461          |
+| 0.0426        | 2.1739 | 150  | 0.3373          |
+| 0.0383        | 2.3188 | 160  | 0.3249          |
+| 0.037         | 2.4638 | 170  | 0.3150          |
+| 0.0516        | 2.6087 | 180  | 0.2967          |
+| 0.0403        | 2.7536 | 190  | 0.2888          |
+| 0.045         | 2.8986 | 200  | 0.2782          |
+| 0.0365        | 3.0435 | 210  | 0.2668          |
+| 0.0309        | 3.1884 | 220  | 0.2598          |
+| 0.0341        | 3.3333 | 230  | 0.2542          |
+| 0.0289        | 3.4783 | 240  | 0.2487          |
+| 0.0364        | 3.6232 | 250  | 0.2417          |
+| 0.0353        | 3.7681 | 260  | 0.2372          |
+| 0.0312        | 3.9130 | 270  | 0.2293          |
+| 0.0317        | 4.0580 | 280  | 0.2263          |
+| 0.029         | 4.2029 | 290  | 0.2254          |
+| 0.0348        | 4.3478 | 300  | 0.2168          |
+| 0.0299        | 4.4928 | 310  | 0.2101          |
+| 0.0327        | 4.6377 | 320  | 0.2085          |
+| 0.0252        | 4.7826 | 330  | 0.2071          |
+| 0.0246        | 4.9275 | 340  | 0.2020          |
+| 0.0219        | 5.0725 | 350  | 0.1990          |
+| 0.0234        | 5.2174 | 360  | 0.1997          |
+| 0.0269        | 5.3623 | 370  | 0.1969          |
+| 0.0262        | 5.5072 | 380  | 0.1961          |
+| 0.0293        | 5.6522 | 390  | 0.1920          |
+| 0.0247        | 5.7971 | 400  | 0.1891          |
+| 0.0273        | 5.9420 | 410  | 0.1869          |
+| 0.0205        | 6.0870 | 420  | 0.1866          |
+| 0.0168        | 6.2319 | 430  | 0.1860          |
+| 0.0261        | 6.3768 | 440  | 0.1851          |
+| 0.0254        | 6.5217 | 450  | 0.1839          |
+| 0.0258        | 6.6667 | 460  | 0.1830          |
+| 0.0242        | 6.8116 | 470  | 0.1825          |
+| 0.0259        | 6.9565 | 480  | 0.1818          |
+| 0.0234        | 7.1014 | 490  | 0.1813          |
+| 0.0194        | 7.2464 | 500  | 0.1812          |
+
+
+### 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:d4bcd36e6a4c4fc6caa27166dd074e7ccd99184beb1c732ccbfe524bf95873a6
+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_12-40-35_gglabs-a6000/events.out.tfevents.1735234835.gglabs-a6000

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c971b1f75a826a0169a27a4ec4a97a434b08e812831f12ac5e80ce119b805a1
+size 30653

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6798c140dfcff7541c0ebc5cd397323d06472eabe148fbaa6f22c25933c8658
+size 5496