End of training

README.md

@@ -0,0 +1,94 @@
+---
+library_name: peft
+language:
+- it
+license: apache-2.0
+base_model: openai/whisper-medium
+tags:
+- generated_from_trainer
+datasets:
+- b-brave-clean
+metrics:
+- wer
+model-index:
+- name: Whisper Medium
+  results:
+  - task:
+      type: automatic-speech-recognition
+      name: Automatic Speech Recognition
+    dataset:
+      name: b-brave-clean
+      type: b-brave-clean
+      config: default
+      split: test
+      args: default
+    metrics:
+    - type: wer
+      value: 76.07449856733524
+      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. -->
+
+# Whisper Medium
+
+This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the b-brave-clean dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7540
+- Wer: 76.0745
+- Cer: 60.6514
+- Lr: 0.0000
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
+- optimizer: Use 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_ratio: 0.3
+- num_epochs: 10
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Wer      | Cer     | Lr     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:-------:|:------:|
+| 3.7378        | 1.0   | 251  | 3.4955          | 122.6361 | 91.8308 | 0.0000 |
+| 1.1797        | 2.0   | 502  | 1.1534          | 80.6590  | 50.3546 | 0.0001 |
+| 0.9184        | 3.0   | 753  | 0.9837          | 71.3467  | 45.7578 | 0.0001 |
+| 0.6271        | 4.0   | 1004 | 0.8690          | 90.2579  | 72.3667 | 0.0001 |
+| 0.4524        | 5.0   | 1255 | 0.8207          | 79.3696  | 66.6141 | 0.0001 |
+| 0.3238        | 6.0   | 1506 | 0.7704          | 80.2292  | 68.0063 | 0.0001 |
+| 0.2246        | 7.0   | 1757 | 0.7517          | 77.9370  | 61.9648 | 0.0000 |
+| 0.1642        | 8.0   | 2008 | 0.7447          | 56.5903  | 38.1928 | 0.0000 |
+| 0.1172        | 9.0   | 2259 | 0.7502          | 79.0831  | 62.9892 | 0.0000 |
+| 0.0787        | 10.0  | 2510 | 0.7540          | 76.0745  | 60.6514 | 0.0000 |
+
+
+### Framework versions
+
+- PEFT 0.14.0
+- Transformers 4.48.3
+- Pytorch 2.2.0
+- Datasets 3.2.0
+- Tokenizers 0.21.0

adapter_config.json

@@ -0,0 +1,36 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "WhisperForConditionalGeneration",
+    "parent_library": "transformers.models.whisper.modeling_whisper"
+  },
+  "base_model_name_or_path": "openai/whisper-medium",
+  "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": 0.3,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "k_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 sha256:29b3ff2a85199993eeb2fda54e10814abc0ca9417f24b00f07d5346fd489beb4
+size 56685000

preprocessor_config.json

@@ -0,0 +1,14 @@
+{
+  "chunk_length": 30,
+  "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
+}

runs/Feb14_19-57-16_e7511933f02a/events.out.tfevents.1739563463.e7511933f02a

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77903d20ded2a1fdcd5d4f35a521db826468bcf0458bb79db04feee772e7e252
+size 6826

runs/Feb14_20-05-14_e7511933f02a/events.out.tfevents.1739563517.e7511933f02a

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99d3d51e6f51f9436d54e42f2a4f1d3dbe026f1a3ba2606dbc07b39d6e16f8e5
+size 32370

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77c07e6a08fe5fb8627c0da1abb6413c4aa8aa59b19f4bcf09d29412b54263a8
+size 5496