Wav2vec2 Large Xlsr Hindi

🚀 Wav2Vec2-Large-XLSR-53-Hindi

This model is a fine - tuned version of facebook/wav2vec2-large-xlsr-53 on Hindi. It addresses the need for accurate Hindi automatic speech recognition by leveraging multiple well - balanced datasets, offering a reliable solution for speech - related tasks in the Hindi language.

Model Information

Results

The model has been evaluated on the following tasks and datasets:

• Task: Speech Recognition (Automatic Speech Recognition)
• Datasets:
  • Common Voice hi: WER of 56.46%
  • Custom Dataset (from 20% of Indic, IIITH and CV test): WER of 17.23%

License

This model is released under the Apache - 2.0 license.

🚀 Quick Start

When using this model, make sure that your speech input is sampled at 16kHz.

💻 Usage Examples

Basic Usage

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("skylord/wav2vec2-large-xlsr-hindi") 
model = Wav2Vec2ForCTC.from_pretrained("skylord/wav2vec2-large-xlsr-hindi") 

resampler = torchaudio.transforms.Resample(48_000, 16_000)

# Preprocessing the datasets.
# We need to read the aduio files as arrays
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

Good Predictions

Poor Predictions

📚 Documentation

Evaluation

The model can be evaluated 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%

Links to the datasets are provided above. Train - test csv files are shared on the following gdrive links: a. IIITH train test b. Indic TTS train test

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

## Load the datasets
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")
iiith = load_dataset("csv", data_files= {"train": "/workspace/data/hi2/iiit_hi_train.csv", 
                                        "test": "/workspace/data/hi2/iiit_hi_test.csv"}, download_mode="force_redownload")

## Pre-process datasets and concatenate to create test dataset
# Drop columns of common_voice
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']])

## Load model from HF hub

wer = load_metric("wer")

processor = Wav2Vec2Processor.from_pretrained("skylord/wav2vec2-large-xlsr-hindi") 
model = Wav2Vec2ForCTC.from_pretrained("skylord/wav2vec2-large-xlsr-hindi")
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)

# Preprocessing the datasets.
# We need to read the aduio files as arrays

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)

# 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"), 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("skylord/wav2vec2-large-xlsr-hindi") 
model = Wav2Vec2ForCTC.from_pretrained("skylord/wav2vec2-large-xlsr-hindi")
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)

# Preprocessing the datasets.
# We need to read the aduio files as arrays

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)

# 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"), 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 and validation datasets were used for training. The script used for training & wandb dashboard can be found here