Model save

README.md

@@ -0,0 +1,67 @@
+---
+license: apache-2.0
+base_model: openai/whisper-small.en
+tags:
+- generated_from_trainer
+metrics:
+- wer
+model-index:
+- name: checkpoints_1
+  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. -->
+
+# checkpoints_1
+
+This model is a fine-tuned version of [openai/whisper-small.en](https://huggingface.co/openai/whisper-small.en) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0186
+- Wer: 2.9762
+- Cer: 1.0999
+
+## 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: 5e-05
+- train_batch_size: 16
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 1000
+- num_epochs: 1
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step  | Cer    | Validation Loss | Wer    |
+|:-------------:|:------:|:-----:|:------:|:---------------:|:------:|
+| 0.0529        | 0.5716 | 5000  | 3.5532 | 0.0494          | 7.8609 |
+| 0.028         | 1.1432 | 10000 | 5.5656 | 0.0413          | 9.7632 |
+| 0.0298        | 1.7149 | 15000 | 2.9926 | 0.0350          | 6.4210 |
+| 0.0133        | 2.2865 | 20000 | 2.1896 | 0.0322          | 5.0360 |
+| 0.0105        | 2.8581 | 25000 | 2.0795 | 0.0307          | 4.7797 |
+
+
+### Framework versions
+
+- Transformers 4.42.3
+- Pytorch 2.3.1+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,58 @@
+{
+  "_name_or_path": "openai/whisper-small.en",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": [
+    1541
+  ],
+  "bos_token_id": 1546,
+  "classifier_proj_size": 256,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 1546,
+  "dropout": 0.0,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 1541,
+  "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": 12,
+  "num_mel_bins": 80,
+  "pad_token_id": 1541,
+  "scale_embedding": false,
+  "suppress_tokens": [
+    1546,
+    1548,
+    1547,
+    1544,
+    1545,
+    1542
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.3",
+  "use_cache": true,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 1549
+}

generation_config.json

@@ -0,0 +1,101 @@
+{
+  "alignment_heads": [
+    [
+      6,
+      6
+    ],
+    [
+      7,
+      0
+    ],
+    [
+      7,
+      3
+    ],
+    [
+      7,
+      8
+    ],
+    [
+      8,
+      2
+    ],
+    [
+      8,
+      5
+    ],
+    [
+      8,
+      7
+    ],
+    [
+      9,
+      0
+    ],
+    [
+      9,
+      4
+    ],
+    [
+      9,
+      8
+    ],
+    [
+      9,
+      10
+    ],
+    [
+      10,
+      0
+    ],
+    [
+      10,
+      1
+    ],
+    [
+      10,
+      2
+    ],
+    [
+      10,
+      3
+    ],
+    [
+      10,
+      6
+    ],
+    [
+      10,
+      11
+    ],
+    [
+      11,
+      2
+    ],
+    [
+      11,
+      4
+    ]
+  ],
+  "begin_suppress_tokens": [
+    1541
+  ],
+  "bos_token_id": 1546,
+  "decoder_start_token_id": 1546,
+  "eos_token_id": 1541,
+  "is_multilingual": false,
+  "max_initial_timestamp_index": 50,
+  "max_length": 448,
+  "no_timestamps_token_id": 1543,
+  "pad_token_id": 1541,
+  "prev_sot_token_id": 1545,
+  "suppress_tokens": [
+    1546,
+    1548,
+    1547,
+    1544,
+    1545,
+    1542
+  ],
+  "transformers_version": "4.42.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:843fee5c155158d8481d09c9f7589fa2fac7e2b24dff61e6361f262b363ee0b5
+size 817182816

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
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f69fb4ded8615f00095eaf37f2a4dcb4dd6a305513ecdb097b4d301cde57a5f2
+size 7480