Upload 8 files

README.md

@@ -0,0 +1,146 @@
+---
+license: apache-2.0
+base_model: facebook/wav2vec2-xls-r-300m
+tags:
+- generated_from_trainer
+metrics:
+- wer
+- cer
+model-index:
+- name: wav2vec2-large-xls-r-300m-hi
+  results: 
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: Common Voice 15
+      type: mozilla-foundation/common_voice_15_0
+      args: hi
+    metrics:
+      - name: Test WER
+        type: wer
+        value: 0.2934
+      - name: Test CER
+        type: cer
+        value: 0.0786
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: Common Voice 8
+      type: mozilla-foundation/common_voice_8_0
+      args: hi
+    metrics:
+      - name: Test WER
+        type: wer
+        value: 0.5209
+      - name: Test CER
+        type: cer
+        value: 0.1790
+datasets:
+- mozilla-foundation/common_voice_15_0
+language:
+- hi
+library_name: transformers
+pipeline_tag: automatic-speech-recognition
+---
+<!-- 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-xls-r-300m-hi
+
+This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3611
+- Wer: 0.2992
+- Cer: 0.0786
+
+View the results on Kaggle Notebook: https://www.kaggle.com/code/kingabzpro/wav2vec-2-eval
+
+## Evaluation
+
+```python
+import torch
+from datasets import load_dataset, load_metric
+from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
+import librosa
+import unicodedata
+import re
+
+
+test_dataset = load_dataset("mozilla-foundation/common_voice_8_0", "hi", split="test")
+wer = load_metric("wer")
+cer = load_metric("cer")
+
+processor = Wav2Vec2Processor.from_pretrained("kingabzpro/wav2vec2-large-xls-r-300m-hi")
+model = Wav2Vec2ForCTC.from_pretrained("kingabzpro/wav2vec2-large-xls-r-300m-hi")
+model.to("cuda")
+
+
+# Preprocessing the datasets.
+def speech_file_to_array_fn(batch):
+    chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“\%\‘\”\�\’\'\|\&\–]'
+    remove_en = '[A-Za-z]'
+    batch["sentence"] = re.sub(chars_to_ignore_regex, "", batch["sentence"].lower())
+    batch["sentence"] = re.sub(remove_en, "", batch["sentence"]).lower()
+    batch["sentence"] = unicodedata.normalize("NFKC", batch["sentence"])
+
+    speech_array, sampling_rate = librosa.load(batch["path"], sr=16_000)
+    batch["speech"] = speech_array
+    return batch
+
+test_dataset = test_dataset.map(speech_file_to_array_fn)
+
+# Preprocessing the datasets.
+# We need to read the aduio files as arrays
+def evaluate(batch):
+  inputs = processor(batch["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)
+
+  with torch.no_grad():
+      logits = model(inputs.input_values.to("cuda")).logits
+
+      pred_ids = torch.argmax(logits, dim=-1)
+      batch["pred_strings"] = processor.batch_decode(pred_ids, skip_special_tokens=True)
+      return batch
+
+result = test_dataset.map(evaluate, batched=True, batch_size=8)
+
+print("WER: {}".format(wer.compute(predictions=result["pred_strings"], references=result["sentence"])))
+print("CER: {}".format(cer.compute(predictions=result["pred_strings"], references=result["sentence"])))
+
+```
+**WER: 0.5209850206372026**
+
+**CER: 0.17902923538230883**
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 32
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 300
+- num_epochs: 100
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Wer    | Cer    |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
+| 7.0431        | 19.05 | 300  | 3.4423          | 1.0    | 1.0    |
+| 2.3233        | 38.1  | 600  | 0.5965          | 0.4757 | 0.1329 |
+| 0.5676        | 57.14 | 900  | 0.3962          | 0.3584 | 0.0954 |
+| 0.3611        | 76.19 | 1200 | 0.3651          | 0.3190 | 0.0820 |
+| 0.2996        | 95.24 | 1500 | 0.3611          | 0.2992 | 0.0786 |
+
+
+### Framework versions
+
+- Transformers 4.33.0
+- Pytorch 2.0.0
+- Datasets 2.1.0
+- Tokenizers 0.13.3

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 65,
+  "<s>": 64
+}

config.json

@@ -0,0 +1,109 @@
+{
+  "_name_or_path": "facebook/wav2vec2-xls-r-300m",
+  "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": 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": 0.0,
+  "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_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": 63,
+  "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": "4.33.0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 66,
+  "xvector_output_dim": 512
+}

preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

special_tokens_map.json

@@ -0,0 +1,22 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "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:ba2c75a2ae554e1c46e400b58d8b91391c6ab8c243e2e90fb6e343b8b07b2436
+size 4027

vocab.json

@@ -0,0 +1,66 @@
+{
+  "[PAD]": 63,
+  "[UNK]": 62,
+  "|": 0,
+  "ँ": 1,
+  "ं": 2,
+  "ः": 3,
+  "अ": 4,
+  "आ": 5,
+  "इ": 6,
+  "ई": 7,
+  "उ": 8,
+  "ऊ": 9,
+  "ऋ": 10,
+  "ए": 11,
+  "ऐ": 12,
+  "ऑ": 13,
+  "ओ": 14,
+  "औ": 15,
+  "क": 16,
+  "ख": 17,
+  "ग": 18,
+  "घ": 19,
+  "च": 20,
+  "छ": 21,
+  "ज": 22,
+  "झ": 23,
+  "ञ": 24,
+  "ट": 25,
+  "ठ": 26,
+  "ड": 27,
+  "ढ": 28,
+  "ण": 29,
+  "त": 30,
+  "थ": 31,
+  "द": 32,
+  "ध": 33,
+  "न": 34,
+  "प": 35,
+  "फ": 36,
+  "ब": 37,
+  "भ": 38,
+  "म": 39,
+  "य": 40,
+  "र": 41,
+  "ल": 42,
+  "व": 43,
+  "श": 44,
+  "ष": 45,
+  "स": 46,
+  "ह": 47,
+  "़": 48,
+  "ा": 49,
+  "ि": 50,
+  "ी": 51,
+  "ु": 52,
+  "ू": 53,
+  "ृ": 54,
+  "े": 55,
+  "ै": 56,
+  "ॉ": 57,
+  "ो": 58,
+  "ौ": 59,
+  "्": 60,
+  "।": 61
+}