nomnoos37/stt-turbo-0112-v1.8

README.md

@@ -0,0 +1,72 @@
+---
+library_name: peft
+language:
+- ko
+license: mit
+base_model: openai/whisper-large-v3-turbo
+tags:
+- generated_from_trainer
+model-index:
+- name: Whisper Turbo 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 Turbo 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: 0.0940
+
+## 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: 0.001
+- 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: 200
+- training_steps: 1000
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.3061        | 0.5405 | 100  | 0.6169          |
+| 0.107         | 1.0811 | 200  | 0.3840          |
+| 0.0871        | 1.6216 | 300  | 0.3024          |
+| 0.0801        | 2.1622 | 400  | 0.2429          |
+| 0.0608        | 2.7027 | 500  | 0.2094          |
+| 0.0527        | 3.2432 | 600  | 0.1674          |
+| 0.0377        | 3.7838 | 700  | 0.1404          |
+| 0.0316        | 4.3243 | 800  | 0.1230          |
+| 0.0302        | 4.8649 | 900  | 0.1004          |
+| 0.0227        | 5.4054 | 1000 | 0.0940          |
+
+
+### 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": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_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 sha256:8c0875d5362a15baa21014bfba943ffed9c107637eff470b81149d67bb08ae8d
+size 52451624

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/Jan13_08-45-04_gglabs-a6000/events.out.tfevents.1736775904.gglabs-a6000

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91670b65d50208ca6a8ee3ce489390431b22095db144931b2c564eafee1a7077
+size 11460

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:284045918a3b838a97423af0f34a207c439f10488c9506185ac5c82eff13fe5e
+size 5496