arslanarjumand/wav2vec-reptiles

README.md

@@ -0,0 +1,69 @@
+---
+license: apache-2.0
+base_model: vitouphy/wav2vec2-xls-r-300m-english
+tags:
+- generated_from_trainer
+model-index:
+- name: wav2vec-reptiles
+  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-reptiles
+
+This model is a fine-tuned version of [vitouphy/wav2vec2-xls-r-300m-english](https://huggingface.co/vitouphy/wav2vec2-xls-r-300m-english) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2223.3787
+- Pcc Accuracy: 0.2187
+- Pcc Fluency: 0.0834
+- Pcc Total Score: 0.1532
+- Pcc Content: 0.2235
+
+## 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: 4
+- eval_batch_size: 6
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.4
+- num_epochs: 25
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Pcc Accuracy | Pcc Fluency | Pcc Total Score | Pcc Content |
+|:-------------:|:-----:|:----:|:---------------:|:------------:|:-----------:|:---------------:|:-----------:|
+| 2728.7846     | 5.0   | 100  | 3196.0576       | 0.3476       | -0.2327     | -0.3110         | 0.2340      |
+| 2491.7434     | 10.0  | 200  | 2875.6025       | 0.2791       | -0.0388     | -0.0724         | 0.2475      |
+| 1926.2301     | 15.0  | 300  | 2480.8772       | 0.2280       | 0.0499      | 0.1131          | 0.2334      |
+| 2065.1381     | 20.0  | 400  | 2265.0391       | 0.2201       | 0.0799      | 0.1478          | 0.2238      |
+| 1903.073      | 25.0  | 500  | 2223.3787       | 0.2187       | 0.0834      | 0.1532          | 0.2235      |
+
+
+### Framework versions
+
+- Transformers 4.37.0
+- Pytorch 2.1.2
+- Datasets 2.17.0
+- Tokenizers 0.15.1

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 30,
+  "<s>": 29
+}

config.json

@@ -0,0 +1,109 @@
+{
+  "_name_or_path": "vitouphy/wav2vec2-xls-r-300m-english",
+  "activation_dropout": 0.006,
+  "adapter_attn_dim": null,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForWav2Vec2ForCTCAndUttranceRegression"
+  ],
+  "attention_dropout": 0.0094,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 768,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": true,
+  "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": true,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": true,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.0,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0005,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu_new",
+  "hidden_dropout": 0.004,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0005,
+  "mask_feature_length": 5,
+  "mask_feature_min_masks": 2,
+  "mask_feature_prob": 0.0075,
+  "mask_time_length": 5,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.0085,
+  "model_type": "wav2vec2",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 16,
+  "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": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 28,
+  "proj_codevector_dim": 768,
+  "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_weighted_layer_sum": false,
+  "vocab_size": 31,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d03ae21377669660184c9ffc98e3b22fc8fc609e5e7c5633f51c53ad78a8336
+size 1261874520

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": true,
+  "sampling_rate": 16000
+}

special_tokens_map.json

@@ -0,0 +1,28 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": "<s>",
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,52 @@
+{
+  "added_tokens_decoder": {
+    "27": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "28": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "29": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "processor_class": "Wav2Vec2Processor",
+  "replace_word_delimiter_char": " ",
+  "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 sha256:2f54219229ffd0652e89c138b196f81421a689404ecbfedf03264f45dd509842
+size 4664

vocab.json

@@ -0,0 +1,31 @@
+{
+  "[PAD]": 28,
+  "[UNK]": 27,
+  "a": 1,
+  "b": 2,
+  "c": 3,
+  "d": 4,
+  "e": 5,
+  "f": 6,
+  "g": 7,
+  "h": 8,
+  "i": 9,
+  "j": 10,
+  "k": 11,
+  "l": 12,
+  "m": 13,
+  "n": 14,
+  "o": 15,
+  "p": 16,
+  "q": 17,
+  "r": 18,
+  "s": 19,
+  "t": 20,
+  "u": 21,
+  "v": 22,
+  "w": 23,
+  "x": 24,
+  "y": 25,
+  "z": 26,
+  "|": 0
+}