Upload folder using huggingface_hub

README.md

@@ -0,0 +1,60 @@
+---
+language:
+- kmr
+license: mit
+library_name: transformers
+tags:
+- automatic-speech-recognition
+- wav2vec2-bert
+- kurdish
+- badini
+- kurmanji
+- low-resource
+base_model: facebook/w2v-bert-2.0
+pipeline_tag: automatic-speech-recognition
+---
+
+# Badini Kurdish ASR (Wav2Vec2-BERT)
+
+An automatic speech recognition (ASR) model for **Badini Kurdish** (a variety of
+Kurmanji, written in Arabic script), fine-tuned from
+[`facebook/w2v-bert-2.0`](https://huggingface.co/facebook/w2v-bert-2.0)
+with a CTC head.
+
+
+## Input requirements
+
+- Audio must be **16 kHz, mono**.
+- Resample any other sample rate to 16 kHz before running inference.
+
+## Usage
+
+```python
+import torch, soundfile as sf
+from transformers import Wav2Vec2BertForCTC, Wav2Vec2BertProcessor
+
+repo_id = "computeram/badini-w2v-bert"
+processor = Wav2Vec2BertProcessor.from_pretrained(repo_id)
+model = Wav2Vec2BertForCTC.from_pretrained(repo_id).eval()
+
+speech, sr = sf.read("audio.wav")   # 16 kHz mono
+inputs = processor(speech, sampling_rate=16000, return_tensors="pt")
+with torch.no_grad():
+    logits = model(**inputs).logits
+pred_ids = torch.argmax(logits, dim=-1)
+print(processor.batch_decode(pred_ids)[0])
+```
+
+## Important: text normalization
+
+This repository contains **only the acoustic model**. The raw output is plain CTC
+decoding. A separate normalization pipeline — punctuation restoration,
+number-to-word expansion (with Badini-specific remapping), character
+normalization, and word-variant correction — is applied in the downstream
+application and is **not** included here. Output straight from this model will
+not match the fully normalized transcripts.
+
+## Intended use
+
+Speech transcription for Badini Kurdish. Given the WER, best used with
+downstream normalization/post-processing rather than as raw final text.

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 69,
+  "<s>": 68
+}

config.json

@@ -0,0 +1,82 @@
+{
+  "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": 0.05,
+  "bos_token_id": 68,
+  "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": true,
+  "diversity_loss_weight": 0.1,
+  "dtype": "float32",
+  "eos_token_id": 69,
+  "feat_proj_dropout": 0.0,
+  "feat_quantizer_dropout": 0.0,
+  "feature_projection_input_dim": 160,
+  "final_dropout": 0.1,
+  "hidden_act": "swish",
+  "hidden_dropout": 0.1,
+  "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": 0.05,
+  "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": 67,
+  "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
+  ],
+  "transformers_version": "5.13.0",
+  "use_cache": false,
+  "use_intermediate_ffn_before_adapter": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 70,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75f0c7b0ac72f483061cf97d65960e82c6543d8bb100edbcc20e09ef57d2ca7d
+size 2423105760

preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "feature_extractor_type": "SeamlessM4TFeatureExtractor",
+  "feature_size": 80,
+  "num_mel_bins": 80,
+  "padding_side": "right",
+  "padding_value": 1,
+  "return_attention_mask": true,
+  "sampling_rate": 16000,
+  "stride": 2
+}

tokenizer_config.json

@@ -0,0 +1,61 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "|",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "66": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "67": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "68": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "69": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "backend": "custom",
+  "bos_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {
+    "word_delimiter_token": "|"
+  },
+  "pad_token": "[PAD]",
+  "processor_class": "Wav2Vec2BertProcessor",
+  "replace_word_delimiter_char": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,70 @@
+{
+  "!": 1,
+  "\"": 2,
+  "#": 3,
+  "(": 4,
+  ")": 5,
+  "+": 6,
+  ".": 7,
+  ":": 8,
+  "=": 9,
+  "[PAD]": 67,
+  "[UNK]": 66,
+  "`": 10,
+  "|": 0,
+  "«": 11,
+  "»": 12,
+  "×": 13,
+  "ê": 14,
+  "î": 15,
+  "û": 16,
+  "ş": 17,
+  "،": 18,
+  "؛": 19,
+  "؟": 20,
+  "ء": 21,
+  "ئ": 22,
+  "ا": 23,
+  "ب": 24,
+  "ت": 25,
+  "ث": 26,
+  "ج": 27,
+  "ح": 28,
+  "خ": 29,
+  "د": 30,
+  "ذ": 31,
+  "ر": 32,
+  "ز": 33,
+  "س": 34,
+  "ش": 35,
+  "ص": 36,
+  "ض": 37,
+  "ط": 38,
+  "ظ": 39,
+  "ع": 40,
+  "غ": 41,
+  "ف": 42,
+  "ق": 43,
+  "ل": 44,
+  "م": 45,
+  "ن": 46,
+  "ه": 47,
+  "و": 48,
+  "پ": 49,
+  "چ": 50,
+  "ڕ": 51,
+  "ژ": 52,
+  "ڤ": 53,
+  "ک": 54,
+  "گ": 55,
+  "ڵ": 56,
+  "ۆ": 57,
+  "ی": 58,
+  "ێ": 59,
+  "ە": 60,
+  "ݒ": 61,
+  "ݘ": 62,
+  "ݵ": 63,
+  "❝": 64,
+  "❞": 65
+}