End of training

README.md

@@ -0,0 +1,98 @@
+---
+library_name: peft
+language:
+- nl
+license: apache-2.0
+base_model: openai/whisper-large-v2
+tags:
+- base_model:adapter:openai/whisper-large-v2
+- lora
+- transformers
+datasets:
+- jasmin
+- jasmin-cgn
+metrics:
+- wer
+model-index:
+- name: Dutch Whisper - all JASMIN
+  results:
+  - task:
+      type: automatic-speech-recognition
+      name: Automatic Speech Recognition
+    dataset:
+      name: JASMIN-CGN
+      type: jasmin
+    metrics:
+    - type: wer
+      value: 54.56220199393152
+      name: Wer
+---
+
+<!-- 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. -->
+
+# Dutch Whisper - all JASMIN
+
+This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on the JASMIN-CGN dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1430
+- Wer: 54.5622
+
+## 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: 1e-05
+- train_batch_size: 48
+- eval_batch_size: 32
+- 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: 180
+- num_epochs: 3.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Wer     |
+|:-------------:|:------:|:----:|:---------------:|:-------:|
+| 1.1206        | 0.1656 | 100  | 1.1056          | 54.0773 |
+| 0.8186        | 0.3311 | 200  | 0.7618          | 40.6074 |
+| 0.474         | 0.4967 | 300  | 0.3831          | 17.4794 |
+| 0.4099        | 0.6623 | 400  | 0.3431          | 15.7618 |
+| 0.3975        | 0.8278 | 500  | 0.3275          | 14.9274 |
+| 0.3941        | 0.9934 | 600  | 0.3171          | 14.6890 |
+| 0.3916        | 1.1589 | 700  | 0.3095          | 13.5891 |
+| 0.391         | 1.3245 | 800  | 0.3039          | 12.8197 |
+| 0.3765        | 1.4901 | 900  | 0.2995          | 13.0283 |
+| 0.3618        | 1.6556 | 1000 | 0.2955          | 12.9931 |
+| 0.3559        | 1.8212 | 1100 | 0.2923          | 12.9416 |
+| 0.3745        | 1.9868 | 1200 | 0.2895          | 12.9606 |
+| 0.3441        | 2.1523 | 1300 | 0.2875          | 12.9226 |
+| 0.3618        | 2.3179 | 1400 | 0.2862          | 12.8116 |
+| 0.351         | 2.4834 | 1500 | 0.2849          | 12.8224 |
+| 0.3399        | 2.6490 | 1600 | 0.2840          | 12.7899 |
+| 1.1391        | 2.8146 | 1700 | 1.1532          | 54.6489 |
+| 1.1297        | 2.9801 | 1800 | 1.1430          | 54.5622 |
+
+
+### Framework versions
+
+- PEFT 0.16.0
+- Transformers 4.52.0
+- Pytorch 2.7.1+cu126
+- Datasets 3.6.0
+- Tokenizers 0.21.2

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "WhisperForConditionalGeneration",
+    "parent_library": "transformers.models.whisper.modeling_whisper"
+  },
+  "base_model_name_or_path": "openai/whisper-large-v2",
+  "bias": "none",
+  "corda_config": null,
+  "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": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": null,
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff6c797d086c4cd9f46467aadf539f41482fd747464a5697c24faed7a6838fa1
+size 62969640

adapter_model/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "WhisperForConditionalGeneration",
+    "parent_library": "transformers.models.whisper.modeling_whisper"
+  },
+  "base_model_name_or_path": "openai/whisper-large-v2",
+  "bias": "none",
+  "corda_config": null,
+  "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": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": null,
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff6c797d086c4cd9f46467aadf539f41482fd747464a5697c24faed7a6838fa1
+size 62969640

preprocessor_config.json

@@ -0,0 +1,15 @@
+{
+  "chunk_length": 30,
+  "dither": 0.0,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 80,
+  "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
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8573a35fdfdc6aa1b7cde4a89229c5ffbcc330d8eac0689ad7c5f85e6ba79b2e
+size 5905