arslanarjumand/wav2vec-read-aloud

README.md

@@ -0,0 +1,70 @@
+---
+license: mit
+base_model: facebook/w2v-bert-2.0
+tags:
+- generated_from_trainer
+model-index:
+- name: wav2vec-read_aloud
+  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. -->
+
+# wav2vec-read_aloud
+
+This model is a fine-tuned version of [facebook/w2v-bert-2.0](https://huggingface.co/facebook/w2v-bert-2.0) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 973.4864
+- Pcc Accuracy: 0.7547
+- Pcc Fluency: 0.7664
+- Pcc Total Score: 0.8143
+- Pcc Content: nan
+
+## 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: 5.5e-05
+- train_batch_size: 2
+- eval_batch_size: 6
+- seed: 42
+- gradient_accumulation_steps: 12
+- total_train_batch_size: 24
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.4
+- num_epochs: 15
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Pcc Accuracy | Pcc Fluency | Pcc Total Score | Pcc Content |
+|:-------------:|:-----:|:----:|:---------------:|:------------:|:-----------:|:---------------:|:-----------:|
+| 2390.3109     | 1.95  | 500  | 2342.6951       | nan          | 0.4815      | nan             | nan         |
+| 2164.6891     | 3.9   | 1000 | 2318.7217       | nan          | 0.6461      | nan             | nan         |
+| 1078.8019     | 5.85  | 1500 | 1029.2085       | 0.6188       | 0.7014      | 0.6845          | nan         |
+| 974.6556      | 7.8   | 2000 | 985.5543        | 0.7117       | 0.7355      | 0.7743          | nan         |
+| 1002.623      | 9.75  | 2500 | 989.1628        | 0.7401       | 0.7533      | 0.7995          | nan         |
+| 947.5643      | 11.7  | 3000 | 972.3806        | 0.7507       | 0.7628      | 0.8103          | nan         |
+| 995.6286      | 13.65 | 3500 | 973.4864        | 0.7547       | 0.7664      | 0.8143          | nan         |
+
+
+### Framework versions
+
+- Transformers 4.37.0
+- Pytorch 2.1.2
+- Datasets 2.18.0
+- Tokenizers 0.15.1

config.json

@@ -0,0 +1,94 @@
+{
+  "_name_or_path": "facebook/w2v-bert-2.0",
+  "activation_dropout": 0.006,
+  "adapter_act": "relu",
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": false,
+  "architectures": [
+    "Wav2Vec2BertForSequenceClassification"
+  ],
+  "attention_dropout": 0.0094,
+  "bos_token_id": 1,
+  "classifier_proj_size": 128,
+  "codevector_dim": 768,
+  "conformer_conv_dropout": 0.1,
+  "contrastive_logits_temperature": 0.1,
+  "conv_depthwise_kernel_size": 31,
+  "ctc_loss_reduction": "sum",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "eos_token_id": 2,
+  "feat_proj_dropout": 0.0,
+  "feat_quantizer_dropout": 0.0,
+  "feature_projection_input_dim": 160,
+  "final_dropout": 0.0005,
+  "hidden_act": "swish",
+  "hidden_dropout": 0.004,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3
+  },
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0005,
+  "left_max_position_embeddings": 64,
+  "mask_feature_length": 5,
+  "mask_feature_min_masks": 5,
+  "mask_feature_prob": 0.0575,
+  "mask_time_length": 5,
+  "mask_time_min_masks": 5,
+  "mask_time_prob": 0.0585,
+  "max_source_positions": 5000,
+  "model_type": "wav2vec2-bert",
+  "num_adapter_layers": 1,
+  "num_attention_heads": 16,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_hidden_layers": 12,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 0,
+  "position_embeddings_type": "relative_key",
+  "proj_codevector_dim": 768,
+  "right_max_position_embeddings": 8,
+  "rotary_embedding_base": 10000,
+  "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": "4.37.0",
+  "use_intermediate_ffn_before_adapter": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": null,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4660acd2a4de557833aa1ce4fbd7ab93333e7c01cf645ab396a4e3a220db11a
+size 1206994592

preprocessor_config.json

@@ -0,0 +1,11 @@
+{
+  "feature_extractor_type": "SeamlessM4TFeatureExtractor",
+  "feature_size": 80,
+  "num_mel_bins": 80,
+  "padding_side": "right",
+  "padding_value": 1,
+  "processor_class": "Wav2Vec2BertProcessor",
+  "return_attention_mask": true,
+  "sampling_rate": 16000,
+  "stride": 2
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:596191023888232fe0a588808a22c46817c7b68e607063d9fa88732a803e892a
+size 4728