emonidi/whisper-order-finetuned-bg

README.md

@@ -0,0 +1,68 @@
+---
+license: apache-2.0
+base_model: nandovallec/whisper-tiny-bg-l
+tags:
+- generated_from_trainer
+metrics:
+- wer
+model-index:
+- name: whisper-tiny-order
+  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-tiny-order
+
+This model is a fine-tuned version of [nandovallec/whisper-tiny-bg-l](https://huggingface.co/nandovallec/whisper-tiny-bg-l) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0022
+- Wer: 0.0
+
+## 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: 1
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 64
+- total_train_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- training_steps: 30
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Wer |
+|:-------------:|:-----:|:----:|:---------------:|:---:|
+| 0.0186        | 4.0   | 5    | 0.0621          | 5.0 |
+| 0.008         | 8.0   | 10   | 0.0235          | 0.0 |
+| 0.0018        | 12.0  | 15   | 0.0049          | 0.0 |
+| 0.001         | 16.0  | 20   | 0.0030          | 0.0 |
+| 0.0005        | 20.0  | 25   | 0.0024          | 0.0 |
+| 0.0007        | 24.0  | 30   | 0.0022          | 0.0 |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.15.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,52 @@
+{
+  "_name_or_path": "nandovallec/whisper-tiny-bg-l",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "classifier_proj_size": 256,
+  "d_model": 384,
+  "decoder_attention_heads": 6,
+  "decoder_ffn_dim": 1536,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 4,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "encoder_attention_heads": 6,
+  "encoder_ffn_dim": 1536,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 4,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": null,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "max_length": 448,
+  "max_source_positions": 1500,
+  "max_target_positions": 448,
+  "median_filter_width": 7,
+  "model_type": "whisper",
+  "num_hidden_layers": 4,
+  "num_mel_bins": 80,
+  "pad_token_id": 50257,
+  "scale_embedding": false,
+  "suppress_tokens": [],
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "use_cache": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51865
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "decoder_start_token_id": 50258,
+  "eos_token_id": 50257,
+  "max_length": 448,
+  "pad_token_id": 50257,
+  "return_timestamps": false,
+  "suppress_tokens": [],
+  "transformers_version": "4.35.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ebcc78eb8c7f9110147cf3eb8464d0490e5b7817fe5229ea6e72ce0c8a2be89
+size 151061672

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/Dec21_15-55-58_d760a204a7bf/events.out.tfevents.1703174261.d760a204a7bf.175.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22c52d75cfb356188945026ba4b0e1332a7425c4defd2a147da9484c0cdef32d
+size 11538

runs/Dec21_15-59-23_d760a204a7bf/events.out.tfevents.1703174367.d760a204a7bf.175.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:340eba8a41de0c93cb94cbbea701608127fa7f50b6da6a8c397d8b151bbf1962
+size 11883

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dce71434c2b32314036c2a222fd8ca9beb66f57309d9f197fa208402ed47009
+size 4728