add model

README.md

@@ -0,0 +1,68 @@
+---
+
+model-index:
+- name: wav2vec2-large-xlsr-arabic-common_voice-10_epochs
+---
+
+<!-- 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. -->
+
+# wav2vec2-large-xlsr-arabic-common_voice-10_epochs
+
+This model was trained from scratch on an unkown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3581
+- Wer: 0.4555
+
+## 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: 0.0003
+- train_batch_size: 16
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 10
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Wer    |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 3.1701        | 0.9   | 400  | 3.1599          | 1.0    |
+| 0.8933        | 1.8   | 800  | 0.7198          | 0.7877 |
+| 0.5849        | 2.7   | 1200 | 0.5046          | 0.6253 |
+| 0.3858        | 3.6   | 1600 | 0.4247          | 0.5561 |
+| 0.3083        | 4.49  | 2000 | 0.4026          | 0.5251 |
+| 0.2556        | 5.39  | 2400 | 0.4010          | 0.5051 |
+| 0.2221        | 6.29  | 2800 | 0.3765          | 0.4861 |
+| 0.2026        | 7.19  | 3200 | 0.3652          | 0.4794 |
+| 0.1996        | 8.09  | 3600 | 0.3627          | 0.4660 |
+| 0.1755        | 8.99  | 4000 | 0.3582          | 0.4619 |
+| 0.1697        | 9.89  | 4400 | 0.3581          | 0.4555 |
+
+
+### Framework versions
+
+- Transformers 4.6.0
+- Pytorch 1.8.1+cu102
+- Datasets 1.6.2
+- Tokenizers 0.10.2

config.json

@@ -0,0 +1,76 @@
+{
+  "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
+  "activation_dropout": 0.0,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 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": false,
+  "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,
+  "final_dropout": 0.0,
+  "gradient_checkpointing": true,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "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_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.05,
+  "mask_time_selection": "static",
+  "model_type": "wav2vec2",
+  "num_attention_heads": 16,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 24,
+  "pad_token_id": 38,
+  "transformers_version": "4.6.0",
+  "vocab_size": 39
+}

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

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81047acba53e007063d753d3172804db1d4817a8aa504ce000775ed27a67ab52
+size 1262093719