Upload noLM model

README.md

@@ -0,0 +1,81 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+model-index:
+- name: MilladRN
+  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. -->
+
+# MilladRN
+
+This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.4355
+- Wer: 0.4907
+- Cer: 0.2802
+
+## 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: 0.0001
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 4000
+- num_epochs: 750
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step  | Validation Loss | Wer    | Cer    |
+|:-------------:|:------:|:-----:|:---------------:|:------:|:------:|
+| 3.3347        | 33.9   | 2000  | 2.2561          | 0.9888 | 0.6087 |
+| 1.3337        | 67.8   | 4000  | 1.8137          | 0.6877 | 0.3407 |
+| 0.6504        | 101.69 | 6000  | 2.0718          | 0.6245 | 0.3229 |
+| 0.404         | 135.59 | 8000  | 2.2246          | 0.6004 | 0.3221 |
+| 0.2877        | 169.49 | 10000 | 2.2624          | 0.5836 | 0.3107 |
+| 0.2149        | 203.39 | 12000 | 2.3788          | 0.5279 | 0.2802 |
+| 0.1693        | 237.29 | 14000 | 1.8928          | 0.5502 | 0.2937 |
+| 0.1383        | 271.19 | 16000 | 2.7520          | 0.5725 | 0.3103 |
+| 0.1169        | 305.08 | 18000 | 2.2552          | 0.5446 | 0.2968 |
+| 0.1011        | 338.98 | 20000 | 2.6794          | 0.5725 | 0.3119 |
+| 0.0996        | 372.88 | 22000 | 2.4704          | 0.5595 | 0.3142 |
+| 0.0665        | 406.78 | 24000 | 2.9073          | 0.5836 | 0.3194 |
+| 0.0538        | 440.68 | 26000 | 3.1357          | 0.5632 | 0.3213 |
+| 0.0538        | 474.58 | 28000 | 2.5639          | 0.5613 | 0.3091 |
+| 0.0493        | 508.47 | 30000 | 3.3801          | 0.5613 | 0.3119 |
+| 0.0451        | 542.37 | 32000 | 3.5469          | 0.5428 | 0.3158 |
+| 0.0307        | 576.27 | 34000 | 4.2243          | 0.5390 | 0.3126 |
+| 0.0301        | 610.17 | 36000 | 3.6666          | 0.5297 | 0.2929 |
+| 0.0269        | 644.07 | 38000 | 3.2164          | 0.5    | 0.2838 |
+| 0.0182        | 677.97 | 40000 | 3.0557          | 0.4963 | 0.2779 |
+| 0.0191        | 711.86 | 42000 | 3.5190          | 0.5130 | 0.2921 |
+| 0.0133        | 745.76 | 44000 | 3.4355          | 0.4907 | 0.2802 |
+
+
+### Framework versions
+
+- Transformers 4.17.0
+- Pytorch 1.12.0+cu113
+- Datasets 1.18.3
+- Tokenizers 0.12.1

config.json

@@ -0,0 +1,117 @@
+{
+  "_name_or_path": "facebook/wav2vec2-base",
+  "activation_dropout": 0.0,
+  "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": 0.0,
+  "freeze_feat_extract_train": true,
+  "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_channel_length": 10,
+  "mask_channel_min_space": 1,
+  "mask_channel_other": 0.0,
+  "mask_channel_prob": 0.0,
+  "mask_channel_selection": "static",
+  "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_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.05,
+  "mask_time_selection": "static",
+  "model_type": "wav2vec2",
+  "no_mask_channel_overlap": false,
+  "no_mask_time_overlap": false,
+  "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": 28,
+  "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": "4.17.0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 31,
+  "xvector_output_dim": 512
+}

preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33a9afac07ef40ad0084001b6d7c63046a082eeb474c7a649de58dd7fcb8a513
+size 377668439

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "replace_word_delimiter_char": " ", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e52a7b9415a27253f1ba7719063d57f1e88d69479dcbf7183a3da57ba6fa2dfb
+size 3055

vocab.json

@@ -0,0 +1 @@
+{"g": 1, "p": 2, "j": 3, "n": 4, "c": 5, "'": 6, "s": 7, "m": 8, "o": 9, "r": 10, "a": 11, "u": 12, "e": 13, "d": 14, "f": 15, "x": 16, "y": 17, "w": 18, "l": 19, "b": 20, "h": 21, "k": 22, "i": 23, "v": 24, "z": 25, "t": 26, "[UNK]": 27, "[PAD]": 28, "|": 0}