Initial commit for wav2vec2facebook-ft-5gram

README.md

@@ -0,0 +1,67 @@
+---
+license: apache-2.0
+base_model: facebook/wav2vec2-base-960h
+tags:
+- generated_from_trainer
+metrics:
+- wer
+model-index:
+- name: wav2vec2-960h-fine-tuning-2
+ 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. -->
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/ashe194-700/facebook-wav-2-vec-fine-tuning/runs/aso83mbs)
+# wav2vec2-960h-fine-tuning-2
+
+This model is a fine-tuned version of [facebook/wav2vec2-base-960h](https://huggingface.co/facebook/wav2vec2-base-960h) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9325
+- Wer: 11.2741
+
+## 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: 4e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 4
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Wer |
+|:-------------:|:------:|:----:|:---------------:|:-------:|
+| No log | 0.9935 | 76 | 1.3301 | 15.9156 |
+| No log | 2.0 | 153 | 3.8761 | 17.1732 |
+| No log | 2.9935 | 229 | 1.8980 | 13.3403 |
+| No log | 3.9739 | 304 | 0.9325 | 11.2741 |
+
+
+### Framework versions
+
+- Transformers 4.42.3
+- Pytorch 2.3.1+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

added_tokens.json

@@ -0,0 +1,4 @@
+{
+ "</s>": 31,
+ "<s>": 30
+}

config.json

@@ -0,0 +1,107 @@
+{
+ "_name_or_path": "facebook/wav2vec2-base-960h",
+ "activation_dropout": 0.1,
+ "adapter_attn_dim": null,
+ "adapter_kernel_size": 3,
+ "adapter_stride": 2,
+ "add_adapter": false,
+ "apply_spec_augment": true,
+ "architectures": [
+ "Wav2Vec2ForCTC"
+ ],
+ "attention_dropout": 0.1,
+ "bos_token_id": 1,
+ "classifier_proj_size": 256,
+ "codevector_dim": 256,
+ "contrastive_logits_temperature": 0.1,
+ "conv_bias": false,
+ "conv_dim": [
+ 512,
+ 512,
+ 512,
+ 512,
+ 512,
+ 512,
+ 512
+ ],
+ "conv_kernel": [
+ 10,
+ 3,
+ 3,
+ 3,
+ 3,
+ 2,
+ 2
+ ],
+ "conv_stride": [
+ 5,
+ 2,
+ 2,
+ 2,
+ 2,
+ 2,
+ 2
+ ],
+ "ctc_loss_reduction": "mean",
+ "ctc_zero_infinity": false,
+ "diversity_loss_weight": 0.1,
+ "do_stable_layer_norm": false,
+ "eos_token_id": 2,
+ "feat_extract_activation": "gelu",
+ "feat_extract_norm": "group",
+ "feat_proj_dropout": 0.0,
+ "feat_quantizer_dropout": 0.0,
+ "final_dropout": 0.1,
+ "hidden_act": "gelu",
+ "hidden_dropout": 0.1,
+ "hidden_size": 768,
+ "initializer_range": 0.02,
+ "intermediate_size": 3072,
+ "layer_norm_eps": 1e-05,
+ "layerdrop": 0.1,
+ "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,
+ "model_type": "wav2vec2",
+ "num_adapter_layers": 3,
+ "num_attention_heads": 12,
+ "num_codevector_groups": 2,
+ "num_codevectors_per_group": 320,
+ "num_conv_pos_embedding_groups": 16,
+ "num_conv_pos_embeddings": 128,
+ "num_feat_extract_layers": 7,
+ "num_hidden_layers": 12,
+ "num_negatives": 100,
+ "output_hidden_size": 768,
+ "pad_token_id": 0,
+ "proj_codevector_dim": 256,
+ "tdnn_dilation": [
+ 1,
+ 2,
+ 3,
+ 1,
+ 1
+ ],
+ "tdnn_dim": [
+ 512,
+ 512,
+ 512,
+ 512,
+ 1500
+ ],
+ "tdnn_kernel": [
+ 5,
+ 3,
+ 3,
+ 1,
+ 1
+ ],
+ "torch_dtype": "float32",
+ "transformers_version": "4.42.3",
+ "use_weighted_layer_sum": false,
+ "vocab_size": 32,
+ "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bb54389d7a4a9d927383008029dd3b4210fe29fb1a83f58beaf7e62c1aa3fa9
+size 377611120

preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+ "do_normalize": true,
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+ "feature_size": 1,
+ "padding_side": "right",
+ "padding_value": 0.0,
+ "processor_class": "Wav2Vec2Processor",
+ "return_attention_mask": false,
+ "sampling_rate": 16000
+}

runs/Sep10_19-19-03_HASEL-Apollo/events.out.tfevents.1725952744.HASEL-Apollo.1841145.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:241a432d895afb4e6399c2bb878b8ce4592d69dda8cea2992458de33709a1f08
+size 7778

runs/Sep10_19-21-06_HASEL-Apollo/events.out.tfevents.1725952867.HASEL-Apollo.1841454.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1da2b4a18d0a65841f70ecd48f84c26fdc8be644d9b0a5196508d7992a75b04
+size 6806

runs/Sep10_19-26-20_HASEL-Apollo/events.out.tfevents.1725953181.HASEL-Apollo.1841791.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36eb55beb3916a7b351abc0c191ae0a1be775fa432e8b567ff4ec73862699308
+size 7778

runs/Sep10_19-30-15_HASEL-Apollo/events.out.tfevents.1725953416.HASEL-Apollo.1842124.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6078fd932f351da70dae5dc5aa818351fea6c9c2f8bd7f6454f00f026a165f9e
+size 7778

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+ "bos_token": "<s>",
+ "eos_token": "</s>",
+ "pad_token": "<pad>",
+ "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,50 @@
+{
+ "added_tokens_decoder": {
+ "0": {
+ "content": "<pad>",
+ "lstrip": true,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false,
+ "special": false
+ },
+ "1": {
+ "content": "<s>",
+ "lstrip": true,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false,
+ "special": false
+ },
+ "2": {
+ "content": "</s>",
+ "lstrip": true,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false,
+ "special": false
+ },
+ "3": {
+ "content": "<unk>",
+ "lstrip": true,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "bos_token": "<s>",
+ "clean_up_tokenization_spaces": true,
+ "do_lower_case": false,
+ "do_normalize": true,
+ "eos_token": "</s>",
+ "model_max_length": 1000000000000000019884624838656,
+ "pad_token": "<pad>",
+ "processor_class": "Wav2Vec2Processor",
+ "replace_word_delimiter_char": " ",
+ "return_attention_mask": false,
+ "target_lang": null,
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
+ "unk_token": "<unk>",
+ "word_delimiter_token": "|"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6a8474a6cdb9bd5beb288408c68233f179a64cd65514d9d2ecb002f1c52c75c
+size 5112

vocab.json

@@ -0,0 +1,34 @@
+{
+ "'": 27,
+ "</s>": 2,
+ "<pad>": 0,
+ "<s>": 1,
+ "<unk>": 3,
+ "A": 7,
+ "B": 24,
+ "C": 19,
+ "D": 14,
+ "E": 5,
+ "F": 20,
+ "G": 21,
+ "H": 11,
+ "I": 10,
+ "J": 29,
+ "K": 26,
+ "L": 15,
+ "M": 17,
+ "N": 9,
+ "O": 8,
+ "P": 23,
+ "Q": 30,
+ "R": 13,
+ "S": 12,
+ "T": 6,
+ "U": 16,
+ "V": 25,
+ "W": 18,
+ "X": 28,
+ "Y": 22,
+ "Z": 31,
+ "|": 4
+}