Upload folder using huggingface_hub

README.md

@@ -0,0 +1,81 @@
+---
+license: apache-2.0
+base_model: Talha/URDU-ASR
+tags:
+- generated_from_trainer
+datasets:
+- common_voice_13_0
+metrics:
+- wer
+model-index:
+- name: wav2vec2-large-xlsr-53-ur-cv13
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: common_voice_13_0
+      type: common_voice_13_0
+      config: ur
+      split: test
+      args: ur
+    metrics:
+    - name: Wer
+      type: wer
+      value: 0.398777515571202
+---
+
+<!-- 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-53-ur-cv13
+
+This model is a fine-tuned version of [Talha/URDU-ASR](https://huggingface.co/Talha/URDU-ASR) on the common_voice_13_0 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4323
+- Wer: 0.3988
+- Cer: 0.1932
+
+## 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: 3e-05
+- 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_steps: 500
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Wer    | Cer    |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
+| 0.8043        | 1.46  | 250  | 0.5256          | 0.4023 | 0.1949 |
+| 0.5435        | 2.92  | 500  | 0.4381          | 0.3965 | 0.1961 |
+| 0.4827        | 4.39  | 750  | 0.4323          | 0.3988 | 0.1932 |
+
+
+### Framework versions
+
+- Transformers 4.34.1
+- Pytorch 2.1.0+cu118
+- Datasets 2.14.6
+- Tokenizers 0.14.1

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "[PAD]": 51,
+  "[UNK]": 50
+}

alphabet.json

@@ -0,0 +1 @@
+{"labels": ["\u0631", "\u06a9", "\u062b", "\u0621", "\u0639", "\u0622", "\u06cc", "\u0642", "\u0641", "\u0679", "\u0630", "\u063a", "\u06d3", "\u06af", "\u0691", "\u0638", "\u0688", "\u0649", "\u06d2", "\u062a", "\u06c3", "\u0647", "\u064a", "\u06ba", "\u06be", "\u0628", "\u0636", "\u062f", "\u0633", "\u06c2", "\u067e", "\u062e", "\u0623", "\u0632", "\u06c1", "\u0624", "\u0646", "\u0645", "\u0626", "\u062d", "\u0686", "\u0644", "\u0634", "\u0635", " ", "\u0637", "\u0627", "\u0698", "\u0648", "\u062c", "\u2047", ""], "is_bpe": false}

config.json

@@ -0,0 +1,117 @@
+{
+  "_name_or_path": "Talha/URDU-ASR",
+  "activation_dropout": 0.0,
+  "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": 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": 0.0,
+  "gradient_checkpointing": false,
+  "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_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",
+  "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": 51,
+  "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": "4.34.1",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 52,
+  "xvector_output_dim": 512
+}

language_model/5gram.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a40a7e9fd0b22c1c40fa9eafee21d9c0e6729af0c6751bf4aadb664ecddbdc4
+size 7191888

language_model/attrs.json

@@ -0,0 +1 @@
+{"alpha": 0.5, "beta": 1.5, "unk_score_offset": -10.0, "score_boundary": true}

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": "Wav2Vec2ProcessorWithLM",
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e595f3398a386c629b5c3dfe9d478ddc1d0a041cbce439c8e635cdd7398f2cd
+size 1262115562

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b630325bd2cc4136cae190fc3e4de0dd6726cf46c99060d577a10df4ad4db35
+size 14308

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5607538ed31c76b932f88c667bde8c976f9888b0675caf3c36b869402b07647
+size 1064

special_tokens_map.json

@@ -0,0 +1,4 @@
+{
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "added_tokens_decoder": {
+    "50": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "51": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "eos_token": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "processor_class": "Wav2Vec2ProcessorWithLM",
+  "replace_word_delimiter_char": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "tokenizer_file": null,
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

trainer_state.json

@@ -0,0 +1,67 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.970760233918129,
+  "eval_steps": 250,
+  "global_step": 850,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.5e-05,
+      "loss": 0.8043,
+      "step": 250
+    },
+    {
+      "epoch": 1.46,
+      "eval_cer": 0.19486492447697548,
+      "eval_loss": 0.5256313681602478,
+      "eval_runtime": 226.5238,
+      "eval_samples_per_second": 14.586,
+      "eval_steps_per_second": 1.823,
+      "eval_wer": 0.4023366474525127,
+      "step": 250
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 3e-05,
+      "loss": 0.5435,
+      "step": 500
+    },
+    {
+      "epoch": 2.92,
+      "eval_cer": 0.1960657773275714,
+      "eval_loss": 0.4380650520324707,
+      "eval_runtime": 227.8338,
+      "eval_samples_per_second": 14.502,
+      "eval_steps_per_second": 1.813,
+      "eval_wer": 0.3965337150373322,
+      "step": 500
+    },
+    {
+      "epoch": 4.39,
+      "learning_rate": 8.873239436619718e-06,
+      "loss": 0.4827,
+      "step": 750
+    },
+    {
+      "epoch": 4.39,
+      "eval_cer": 0.193239280141815,
+      "eval_loss": 0.4322899878025055,
+      "eval_runtime": 230.4509,
+      "eval_samples_per_second": 14.337,
+      "eval_steps_per_second": 1.792,
+      "eval_wer": 0.398777515571202,
+      "step": 750
+    }
+  ],
+  "logging_steps": 250,
+  "max_steps": 855,
+  "num_train_epochs": 5,
+  "save_steps": 850,
+  "total_flos": 2.8872999396360806e+18,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acef9e4c1fd5be56981ea18a88e15b906fd57cd25e357b0b08174a64407314ec
+size 4600

vocab.json

@@ -0,0 +1,54 @@
+{
+  "[PAD]": 51,
+  "[UNK]": 50,
+  "|": 44,
+  "ء": 3,
+  "آ": 5,
+  "أ": 32,
+  "ؤ": 35,
+  "ئ": 38,
+  "ا": 46,
+  "ب": 25,
+  "ت": 19,
+  "ث": 2,
+  "ج": 49,
+  "ح": 39,
+  "خ": 31,
+  "د": 27,
+  "ذ": 10,
+  "ر": 0,
+  "ز": 33,
+  "س": 28,
+  "ش": 42,
+  "ص": 43,
+  "ض": 26,
+  "ط": 45,
+  "ظ": 15,
+  "ع": 4,
+  "غ": 11,
+  "ف": 8,
+  "ق": 7,
+  "ل": 41,
+  "م": 37,
+  "ن": 36,
+  "ه": 21,
+  "و": 48,
+  "ى": 17,
+  "ي": 22,
+  "ٹ": 9,
+  "پ": 30,
+  "چ": 40,
+  "ڈ": 16,
+  "ڑ": 14,
+  "ژ": 47,
+  "ک": 1,
+  "گ": 13,
+  "ں": 23,
+  "ھ": 24,
+  "ہ": 34,
+  "ۂ": 29,
+  "ۃ": 20,
+  "ی": 6,
+  "ے": 18,
+  "ۓ": 12
+}