Update README.md

add github link

README.md

@@ -0,0 +1,48 @@
+---
+language: en
+datasets:
+- LIUM/tedlium
+tags:
+- speech
+- audio
+- automatic-speech-recognition
+---
+Finetuned from [facebook/wav2vec2-large-960h-lv60-self](https://huggingface.co/facebook/wav2vec2-large-960h-lv60-self).
+
+# Installation
+1. PyTorch installation: https://pytorch.org/
+2. Install transformers: https://huggingface.co/docs/transformers/installation
+
+e.g., installation by conda
+```
+>> conda create -n wav2vec2 python=3.8
+>> conda install pytorch cudatoolkit=11.3 -c pytorch
+>> conda install -c conda-forge transformers
+```
+
+# Usage
+```python
+# Load the model and processor
+from transformers import Wav2Vec2Processor, Wav2Vec2ForCTC
+import numpy as np
+import torch
+
+model = Wav2Vec2ForCTC.from_pretrained(r'yongjian/wav2vec2-large-a') # Note: PyTorch Model
+processor = Wav2Vec2Processor.from_pretrained(r'yongjian/wav2vec2-large-a')
+
+# Load input
+np_wav = np.random.normal(size=(16000)).clip(-1, 1) # change it to your sample
+
+# Inference
+sample_rate = processor.feature_extractor.sampling_rate
+with torch.no_grad():
+    model_inputs = processor(np_wav, sampling_rate=sample_rate, return_tensors="pt", padding=True)
+    logits = model(model_inputs.input_values, attention_mask=model_inputs.attention_mask).logits # use .cuda() for GPU acceleration
+    pred_ids = torch.argmax(logits, dim=-1).cpu()
+    pred_text = processor.batch_decode(pred_ids)
+print('Transcription:', pred_text)
+```
+
+# Code
+GitHub Repo:
+https://github.com/CassiniHuy/wav2vec2_finetune

config.json

@@ -0,0 +1,108 @@
+{
+  "activation_dropout": 0.1,
+  "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": 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": "sum",
+  "ctc_zero_infinity": false,
+  "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": 0.1,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "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,
+  "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": 0,
+  "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": "4.19.4",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32,
+  "xvector_output_dim": 512
+}

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

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+    "unk_token": "<unk>",
+    "bos_token": "<s>",
+    "eos_token": "</s>",
+    "pad_token": "<pad>",
+    "do_lower_case": false,
+    "word_delimiter_token": "|",
+    "replace_word_delimiter_char": " ",
+    "return_attention_mask": true,
+    "do_normalize": true,
+    "processor_class": "Wav2Vec2Processor",
+    "tokenizer_class": "Wav2Vec2CTCTokenizer"
+}

vocab.json

@@ -0,0 +1,34 @@
+{
+    "<pad>": 0,
+    "<s>": 1,
+    "</s>": 2,
+    "<unk>": 3,
+    "|": 4,
+    "E": 5,
+    "T": 6,
+    "A": 7,
+    "O": 8,
+    "N": 9,
+    "I": 10,
+    "H": 11,
+    "S": 12,
+    "R": 13,
+    "D": 14,
+    "L": 15,
+    "U": 16,
+    "M": 17,
+    "W": 18,
+    "C": 19,
+    "F": 20,
+    "G": 21,
+    "Y": 22,
+    "P": 23,
+    "B": 24,
+    "V": 25,
+    "K": 26,
+    "'": 27,
+    "X": 28,
+    "J": 29,
+    "Q": 30,
+    "Z": 31
+}