Upload folder using huggingface_hub

README.md

@@ -0,0 +1,87 @@
+---
+tags:
+- generated_from_trainer
+datasets:
+- common_voice_17_0
+metrics:
+- wer
+model-index:
+- name: w2v2-bert-urdu
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: common_voice_17_0
+      type: common_voice_17_0
+      config: ur
+      split: test[:100]
+      args: ur
+    metrics:
+    - name: Wer
+      type: wer
+      value: 0.3300546448087432
+---
+
+<!-- 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. -->
+
+# w2v2-bert-urdu
+
+This model was trained from scratch on the common_voice_17_0 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4246
+- Wer: 0.3301
+
+## 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-06
+- 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: 100
+- num_epochs: 2
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Wer    |
+|:-------------:|:------:|:----:|:---------------:|:------:|
+| 0.8145        | 0.1695 | 50   | 0.4620          | 0.3421 |
+| 0.4364        | 0.3390 | 100  | 0.3969          | 0.2874 |
+| 0.418         | 0.5085 | 150  | 0.3697          | 0.2820 |
+| 0.402         | 0.6780 | 200  | 0.3627          | 0.2842 |
+| 0.3698        | 0.8475 | 250  | 0.3314          | 0.2710 |
+| 0.3779        | 1.0169 | 300  | 0.3292          | 0.2852 |
+| 0.3167        | 1.1864 | 350  | 0.3230          | 0.2820 |
+| 0.3578        | 1.3559 | 400  | 0.3825          | 0.2940 |
+| 0.4189        | 1.5254 | 450  | 0.4225          | 0.3104 |
+| 0.4803        | 1.6949 | 500  | 0.4248          | 0.3311 |
+| 0.4612        | 1.8644 | 550  | 0.4246          | 0.3301 |
+
+
+### Framework versions
+
+- Transformers 4.40.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 64,
+  "<s>": 63
+}

alphabet.json

@@ -0,0 +1 @@
+{"labels": [" ", "\u0623", "\u0624", "\u0626", "\u0627", "\u0628", "\u062a", "\u062b", "\u062c", "\u062d", "\u062e", "\u062f", "\u0630", "\u0631", "\u0632", "\u0633", "\u0634", "\u0635", "\u0636", "\u0637", "\u0638", "\u0639", "\u063a", "\u0641", "\u0642", "\u0643", "\u0644", "\u0645", "\u0646", "\u0647", "\u0648", "\u064a", "\u0679", "\u067e", "\u0686", "\u0688", "\u0691", "\u0698", "\u06a9", "\u06af", "\u06ba", "\u06be", "\u06c1", "\u06c2", "\u06c3", "\u06cc", "\u06d2", "\u06d3", "\ufb68", "\ufbad", "\ufbaf", "\ufbfe", "\ufdf2", "\ufdfa", "\ufe85", "\ufe97", "\ufe98", "\ufea9", "\ufeb2", "\ufee7", "\ufeee", "\u2047", "", "<s>", "</s>"], "is_bpe": false}

config.json

@@ -0,0 +1,82 @@
+{
+  "_name_or_path": "w2v2-bert-urdu",
+  "activation_dropout": 0.0,
+  "adapter_act": "relu",
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": true,
+  "apply_spec_augment": false,
+  "architectures": [
+    "Wav2Vec2BertForCTC"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "classifier_proj_size": 768,
+  "codevector_dim": 768,
+  "conformer_conv_dropout": 0.1,
+  "contrastive_logits_temperature": 0.1,
+  "conv_depthwise_kernel_size": 31,
+  "ctc_loss_reduction": "mean",
+  "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": 0.1,
+  "hidden_act": "swish",
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "left_max_position_embeddings": 64,
+  "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_prob": 0.0,
+  "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": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 62,
+  "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": "4.40.2",
+  "use_intermediate_ffn_before_adapter": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 65,
+  "xvector_output_dim": 512
+}

language_model/5gram.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e5454facbffe62a26c6781b6b779953e12aad7815b5eb3b03bdd7082f17181a
+size 6366106

language_model/attrs.json

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

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17747e10300fac022a134b42d307ebdfd5b00ee0b2b350da2fd17ec67ff66fab
+size 2423081060

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": "Wav2Vec2ProcessorWithLM",
+  "return_attention_mask": true,
+  "sampling_rate": 16000,
+  "stride": 2
+}

runs/May12_17-18-18_1d4a7576e075/events.out.tfevents.1715534458.1d4a7576e075.1900.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2f3e451abeb3da8bf7175b8a52962c3167ee0e0d59241d65ba9e581e899931a
+size 18118

runs/May12_18-22-06_1d4a7576e075/events.out.tfevents.1715538284.1d4a7576e075.1900.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f86c39156283e6a1025f9d70bc4fed254fbc60859204ec04daff0b4e2f58dabb
+size 12072

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+  "added_tokens_decoder": {
+    "61": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "62": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "63": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "processor_class": "Wav2Vec2ProcessorWithLM",
+  "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 sha256:9a14a5c3359637bb1b3e9fd4d16f8e63f99e460411687da64ccb77020ddd1d84
+size 4984

vocab.json

@@ -0,0 +1,65 @@
+{
+  "[PAD]": 62,
+  "[UNK]": 61,
+  "|": 0,
+  "أ": 1,
+  "ؤ": 2,
+  "ئ": 3,
+  "ا": 4,
+  "ب": 5,
+  "ت": 6,
+  "ث": 7,
+  "ج": 8,
+  "ح": 9,
+  "خ": 10,
+  "د": 11,
+  "ذ": 12,
+  "ر": 13,
+  "ز": 14,
+  "س": 15,
+  "ش": 16,
+  "ص": 17,
+  "ض": 18,
+  "ط": 19,
+  "ظ": 20,
+  "ع": 21,
+  "غ": 22,
+  "ف": 23,
+  "ق": 24,
+  "ك": 25,
+  "ل": 26,
+  "م": 27,
+  "ن": 28,
+  "ه": 29,
+  "و": 30,
+  "ي": 31,
+  "ٹ": 32,
+  "پ": 33,
+  "چ": 34,
+  "ڈ": 35,
+  "ڑ": 36,
+  "ژ": 37,
+  "ک": 38,
+  "گ": 39,
+  "ں": 40,
+  "ھ": 41,
+  "ہ": 42,
+  "ۂ": 43,
+  "ۃ": 44,
+  "ی": 45,
+  "ے": 46,
+  "ۓ": 47,
+  "ﭨ": 48,
+  "ﮭ": 49,
+  "ﮯ": 50,
+  "ﯾ": 51,
+  "ﷲ": 52,
+  "ﷺ": 53,
+  "ﺅ": 54,
+  "ﺗ": 55,
+  "ﺘ": 56,
+  "ﺩ": 57,
+  "ﺲ": 58,
+  "ﻧ": 59,
+  "ﻮ": 60
+}