| Fine-tuned Wav2Vec2 on Hindi using the following datasets: |
|
|
| - [Common Voice](https://huggingface.co/datasets/common_voice), |
|
|
| - [Indic TTS- IITM](https://www.iitm.ac.in/donlab/tts/index.php) |
|
|
|
|
| The Indic datasets are well balanced across gender and accents. However the CommonVoice dataset is skewed towards male voices |
|
|
| Fine-tuned on Wav2Vec2 using Hindi dataset :: 60 epochs >> 17.05% WER |
|
|
| When using this model, make sure that your speech input is sampled at 16kHz. |
|
|
| ## Usage |
|
|
| The model can be used directly (without a language model) as follows: |
|
|
| ```python |
| |
| import torch |
| |
| import torchaudio |
| |
| from datasets import load_dataset |
| |
| from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor |
| |
| test_dataset = load_dataset("common_voice", "hi", split="test") |
| |
| |
| |
| processor = Wav2Vec2Processor.from_pretrained("Maverick1713/Hindi-ASR") |
| |
| model = Wav2Vec2ForCTC.from_pretrained("Maverick1713/Hindi-ASR") |
| |
| |
| |
| resampler = torchaudio.transforms.Resample(48_000, 16_000) |
| |
| |
| |
| |
| def speech_file_to_array_fn(batch): |
| |
| speech_array, sampling_rate = torchaudio.load(batch["path"]) |
| |
| batch["speech"] = resampler(speech_array).squeeze().numpy() |
| |
| return batch |
| |
| |
| |
| test_dataset = test_dataset.map(speech_file_to_array_fn) |
| |
| inputs = processor(test_dataset["speech"][:2], sampling_rate=16_000, return_tensors="pt", padding=True) |
| |
| |
| |
| with torch.no_grad(): |
| |
| logits = model(inputs.input_values, attention_mask=inputs.attention_mask).logits |
| |
| |
| |
| predicted_ids = torch.argmax(logits, dim=-1) |
| |
| print("Prediction:", processor.batch_decode(predicted_ids)) |
| |
| print("Reference:", test_dataset["sentence"][:2]) |
| |
| ``` |
|
|
| ## Predictions |
|
|
| _Some good ones ..... _ |
|
|
| | Predictions | Reference | |
|
|
| |-------|-------| |
|
|
| |फिर वो सूरज तारे पहाड बारिश पदछड़ दिन रात शाम नदी बर्फ़ समुद्र धुंध हवा कुछ भी हो सकती है | फिर वो सूरज तारे पहाड़ बारिश पतझड़ दिन रात शाम नदी बर्फ़ समुद्र धुंध हवा कुछ भी हो सकती है | |
|
|
| | इस कारण जंगल में बडी दूर स्थित राघव के आश्रम में लोघ कम आने लगे और अधिकांश भक्त सुंदर के आश्रम में जाने लगे | इस कारण जंगल में बड़ी दूर स्थित राघव के आश्रम में लोग कम आने लगे और अधिकांश भक्त सुन्दर के आश्रम में जाने लगे | |
|
|
| | अपने बचन के अनुसार शुभमूर्त पर अनंत दक्षिणी पर्वत गया और मंत्रों का जप करके सरोवर में उतरा | अपने बचन के अनुसार शुभमुहूर्त पर अनंत दक्षिणी पर्वत गया और मंत्रों का जप करके सरोवर में उतरा | |
|
|
| _Some crappy stuff .... _ |
|
|
| | Predictions | Reference | |
|
|
| |-------|-------| |
|
|
| | वस गनिल साफ़ है। | उसका दिल साफ़ है। | |
|
|
| | चाय वा एक कुछ लैंगे हब | चायवाय कुछ लेंगे आप | |
|
|
| | टॉम आधे है स्कूल हें है | टॉम अभी भी स्कूल में है | |
|
|
| ## Evaluation |
|
|
| The model can be evaluated as follows on the following two datasets: |
|
|
| 1. Custom dataset created from 20% of Indic, IIITH and CV (test): WER 17.xx% |
|
|
| 2. CommonVoice Hindi test dataset: WER 56.xx% |
|
|
|
|
| Update the audio_path as per your local file structure. |
| |
| ```python |
| |
| import torch |
| |
| import torchaudio |
| |
| from datasets import load_dataset, load_metric |
| |
| from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor |
| |
| import re |
| |
| |
| |
| |
| test_dataset = load_dataset("common_voice", "hi", split="test") |
|
|
|
|
|
|
| indic = load_dataset("csv", data_files= {'train':"/workspace/data/hi2/indic_train_full.csv", |
|
|
| "test": "/workspace/data/hi2/indic_test_full.csv"}, download_mode="force_redownload") |
| |
|
|
|
|
|
|
| split = ['train', 'test', 'validation', 'other', 'invalidated'] |
|
|
|
|
|
|
| for sp in split: |
|
|
| common_voice[sp] = common_voice[sp].remove_columns(['client_id', 'up_votes', 'down_votes', 'age', 'gender', 'accent', 'locale', 'segment']) |
| |
|
|
|
|
| common_voice = common_voice.rename_column('path', 'audio_path') |
|
|
| common_voice = common_voice.rename_column('sentence', 'target_text') |
|
|
|
|
|
|
| train_dataset = datasets.concatenate_datasets([indic['train'], iiith['train'], common_voice['train']]) |
| |
| test_dataset = datasets.concatenate_datasets([indic['test'], iiith['test'], common_voice['test'], common_voice['validation']]) |
| |
| |
| |
| |
| |
| wer = load_metric("wer") |
|
|
|
|
|
|
| processor = Wav2Vec2Processor.from_pretrained("Maverick1713/Hindi-ASR") |
| |
| model = Wav2Vec2ForCTC.from_pretrained("Maverick1713/Hindi-ASR") |
|
|
| model.to("cuda") |
|
|
|
|
|
|
| chars_to_ignore_regex = '[\,\?\.\!\-\'\;\:\"\“\%\‘\”\�Utrnle\_]' |
|
|
| unicode_ignore_regex = r'[dceMaWpmFui\xa0\u200d]' # Some unwanted unicode chars |
|
|
| resampler = torchaudio.transforms.Resample(48_000, 16_000) |
|
|
|
|
|
|
|
|
|
|
| def speech_file_to_array_fn(batch): |
|
|
| batch["target_text"] = re.sub(chars_to_ignore_regex, '', batch["target_text"]) |
| |
| batch["target_text"] = re.sub(unicode_ignore_regex, '', batch["target_text"]) |
| |
| |
| |
| speech_array, sampling_rate = torchaudio.load(batch["audio_path"]) |
|
|
| batch["speech"] = resampler(speech_array).squeeze().numpy() |
| |
| return batch |
| |
| |
| |
| test_dataset = test_dataset.map(speech_file_to_array_fn) |
| |
| |
| |
| |
| 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"), attention_mask=inputs.attention_mask.to("cuda")).logits |
|
|
| pred_ids = torch.argmax(logits, dim=-1) |
| |
| batch["pred_strings"] = processor.batch_decode(pred_ids) |
|
|
| return batch |
|
|
|
|
|
|
| result = test_dataset.map(evaluate, batched=True, batch_size=8) |
|
|
| print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"], references=result["sentence"]))) |
| |
| ``` |
| |
| **Test Result on custom dataset**: 17.23 % |
| |
| ```python |
| |
| import torch |
| |
| import torchaudio |
| |
| from datasets import load_dataset, load_metric |
| |
| from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor |
| |
| import re |
| |
| |
| |
| test_dataset = load_dataset("common_voice", "hi", split="test") |
|
|
| wer = load_metric("wer") |
| |
| |
| |
| processor = Wav2Vec2Processor.from_pretrained("Maverick1713/Hindi-ASR") |
|
|
| model = Wav2Vec2ForCTC.from_pretrained("Maverick1713/Hindi-ASR") |
| |
| model.to("cuda") |
| |
| |
| |
| chars_to_ignore_regex = '[\,\?\.\!\-\'\;\:\"\“\%\‘\”\�Utrnle\_]' |
| |
| unicode_ignore_regex = r'[dceMaWpmFui\xa0\u200d]' |
| |
| resampler = torchaudio.transforms.Resample(48_000, 16_000) |
| |
| |
| |
| |
| |
| def speech_file_to_array_fn(batch): |
| |
| batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).sub(unicode_ignore_regex, '', batch["sentence"]) |
|
|
| speech_array, sampling_rate = torchaudio.load(batch["path"]) |
|
|
| batch["speech"] = resampler(speech_array).squeeze().numpy() |
| |
| return batch |
| |
| |
| |
| test_dataset = test_dataset.map(speech_file_to_array_fn) |
| |
| |
| |
| |
| |
| 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"), attention_mask=inputs.attention_mask.to("cuda")).logits |
|
|
| pred_ids = torch.argmax(logits, dim=-1) |
| |
| batch["pred_strings"] = processor.batch_decode(pred_ids) |
|
|
| return batch |
|
|
|
|
|
|
| result = test_dataset.map(evaluate, batched=True, batch_size=8) |
|
|
| print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"], references=result["sentence"]))) |
| |
| ``` |
| |
| **Test Result on CommonVoice**: 56.46 % |
| |
| ## Training |
| |
| The Common Voice `train`, `validation`, datasets were used for training as well as |
| |
