import soundfile as sf
import torch
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
import argparse

def parse_transcription(wav_file):
    # load pretrained model
    processor = Wav2Vec2Processor.from_pretrained("Harveenchadha/vakyansh-wav2vec2-hindi-him-4200")
    model = Wav2Vec2ForCTC.from_pretrained("Harveenchadha/vakyansh-wav2vec2-hindi-him-4200")

    # load audio
    audio_input, sample_rate = sf.read(wav_file)

    # pad input values and return pt tensor
    input_values = processor(audio_input, sampling_rate=sample_rate, return_tensors="pt").input_values

    # INFERENCE
    # retrieve logits & take argmax
    logits = model(input_values).logits
    predicted_ids = torch.argmax(logits, dim=-1)

    # transcribe
    transcription = processor.decode(predicted_ids[0], skip_special_tokens=True)
    print(transcription)

Evaluation

The model can be evaluated as follows on the hindi test data of Common Voice.

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("Harveenchadha/vakyansh-wav2vec2-hindi-him-4200")
model = Wav2Vec2ForCTC.from_pretrained("Harveenchadha/vakyansh-wav2vec2-hindi-him-4200")
model.to("cuda")

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

chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“]'

# 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"]).lower()
  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")).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: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"], references=result["sentence"])))

Test Result: 33.17 %

Credits

Thanks to Deepmindz Innovations for making this possible.

aditii09/hc_hindi_asr

Dataset

Usage

Evaluation

Credits

aditii09/
hc_hindi_asr