Maverick1713/Hindi-ASR

Fine-tuned Wav2Vec2 on Hindi using the following datasets:

• Common Voice,

• Indic TTS- IITM

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:

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.

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 %

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