Duplicate from asr-nigerian-pidgin/pidgin-wav2vec2-base-100H

Co-authored-by: Amina Mardiyyah Rufai <[email protected]>

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,83 @@
+---
+base_model: facebook/wav2vec2-base
+license: apache-2.0
+metrics:
+- wer
+tags:
+- generated_from_trainer
+model-index:
+- name: pidgin-wav2vec2-base-960h
+  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. -->
+
+# pidgin-wav2vec2-base-960h
+
+This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the [Nigerian Pidgin](https://huggingface.co/datasets/asr-nigerian-pidgin/nigerian-pidgin-1.0) dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0898
+- Wer: 0.3966
+
+## 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: 4
+- eval_batch_size: 4
+- seed: 3407
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 1000
+- num_epochs: 30
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Wer    |
+|:-------------:|:-----:|:-----:|:---------------:|:------:|
+| 4.3949        | 1.48  | 500   | 3.3325          | 0.9999 |
+| 2.4656        | 2.95  | 1000  | 1.4727          | 0.8026 |
+| 1.1896        | 4.43  | 1500  | 1.0925          | 0.6252 |
+| 0.8558        | 5.91  | 2000  | 0.9467          | 0.5422 |
+| 0.6427        | 7.39  | 2500  | 0.9856          | 0.5096 |
+| 0.5371        | 8.86  | 3000  | 0.9794          | 0.5093 |
+| 0.4553        | 10.34 | 3500  | 0.8719          | 0.4641 |
+| 0.3921        | 11.82 | 4000  | 0.9344          | 0.4566 |
+| 0.3406        | 13.29 | 4500  | 1.0211          | 0.4550 |
+| 0.3046        | 14.77 | 5000  | 0.8668          | 0.4423 |
+| 0.2651        | 16.25 | 5500  | 1.0384          | 0.4261 |
+| 0.244         | 17.73 | 6000  | 1.0437          | 0.4296 |
+| 0.2203        | 19.2  | 6500  | 0.9244          | 0.4228 |
+| 0.1995        | 20.68 | 7000  | 0.9832          | 0.4165 |
+| 0.1838        | 22.16 | 7500  | 1.1455          | 0.4112 |
+| 0.1632        | 23.63 | 8000  | 1.1102          | 0.4102 |
+| 0.1576        | 25.11 | 8500  | 1.0769          | 0.4044 |
+| 0.1388        | 26.59 | 9000  | 1.1008          | 0.4013 |
+| 0.1346        | 28.06 | 9500  | 1.0940          | 0.4000 |
+| 0.1204        | 29.54 | 10000 | 1.0898          | 0.3966 |
+
+
+### Framework versions
+
+- Transformers 4.37.2
+- Pytorch 2.0.1+cu117
+- Datasets 2.12.0
+- Tokenizers 0.15.2

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 46,
+  "<s>": 45
+}

config.json

@@ -0,0 +1,118 @@
+{
+  "_name_or_path": "asr-nigerian-pidgin/wav2vec2-base-960h/checkpoint-10000",
+  "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": 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": true,
+  "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": 0.1,
+  "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": 0.0,
+  "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": 44,
+  "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": "4.43.4",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 45,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a949f4f5e9fc448ebd14c000304137d0f68a01cc110c4edb960886c8c0ee4813
+size 377651116

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": false,
+  "sampling_rate": 16000
+}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+  "added_tokens_decoder": {
+    "43": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "44": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "45": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "46": {
+      "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": "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:b96a8547ec93febb076a78b0510127048084853295c74310e5985fa39ded13f0
+size 4347

vocab.json

@@ -0,0 +1,47 @@
+{
+  "'": 4,
+  "/": 1,
+  "0": 3,
+  "1": 34,
+  "2": 22,
+  "3": 41,
+  "4": 28,
+  "5": 12,
+  "6": 14,
+  "7": 31,
+  "8": 26,
+  "9": 39,
+  "@": 17,
+  "[PAD]": 44,
+  "[UNK]": 43,
+  "a": 23,
+  "b": 24,
+  "c": 16,
+  "d": 13,
+  "e": 2,
+  "f": 15,
+  "g": 0,
+  "h": 25,
+  "i": 20,
+  "j": 33,
+  "k": 32,
+  "l": 40,
+  "m": 37,
+  "n": 42,
+  "o": 21,
+  "p": 27,
+  "q": 8,
+  "r": 29,
+  "s": 36,
+  "t": 18,
+  "u": 38,
+  "v": 9,
+  "w": 30,
+  "x": 5,
+  "y": 35,
+  "z": 10,
+  "|": 19,
+  "ç": 6,
+  "è": 11,
+  "é": 7
+}