File size: 4,176 Bytes
863a64d b68f233 863a64d f762a5d cb7ac4f cbeb18d cb7ac4f aafdd3b cb7ac4f cbeb18d cb7ac4f 6caf0bf cb7ac4f 6caf0bf cb7ac4f c68f981 cb7ac4f cbeb18d cb7ac4f 6caf0bf c68f981 6caf0bf cb7ac4f 6caf0bf cb7ac4f 6caf0bf cb7ac4f 6caf0bf cb7ac4f c68f981 ac5d2e5 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 |
---
language: mr
datasets:
- openslr
- interspeech_2021_asr
metrics:
- wer
tags:
- audio
- automatic-speech-recognition
- speech
- xlsr-fine-tuning-week
- hindi
- marathi
license: apache-2.0
model-index:
- name: XLSR Wav2Vec2 Large 53 Hindi-Marathi by Tanmay Laud
results:
- task:
name: Speech Recognition
type: automatic-speech-recognition
dataset:
name: OpenSLR hi, OpenSLR mr
type: openslr, interspeech_2021_asr
metrics:
- name: Test WER
type: wer
value: 24.944955
---
# Wav2Vec2-Large-XLSR-53-Hindi-Marathi
Fine-tuned facebook/wav2vec2-large-xlsr-53 on Hindi and Marathi using the OpenSLR SLR64 datasets. 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, assuming you have a dataset with Marathi text and audio_path fields:
```python
import torch
import torchaudio
import librosa
from datasets import load_dataset
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
# test_data = #TODO: WRITE YOUR CODE TO LOAD THE TEST DATASET. For sample see the Colab link in Training Section.
processor = Wav2Vec2Processor.from_pretrained("tanmaylaud/wav2vec2-large-xlsr-hindi-marathi")
model = Wav2Vec2ForCTC.from_pretrained("tanmaylaud/wav2vec2-large-xlsr-hindi-marathi")
# Preprocessing the datasets.
# We need to read the audio files as arrays
def speech_file_to_array_fn(batch):
speech_array, sampling_rate = torchaudio.load(batch["audio_path"])
batch["speech"] = librosa.resample(speech_array[0].numpy(), sampling_rate, 16_000) # sampling_rate can vary
return batch
test_data= test_data.map(speech_file_to_array_fn)
inputs = processor(test_data["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_data["text"][:2])
Evaluation
The model can be evaluated as follows on 10% of the Marathi data on OpenSLR.
```python
import torchaudio
from datasets import load_metric
from transformers import Wav2Vec2Processor,Wav2Vec2ForCTC
import torch
import librosa
import numpy as np
import re
wer = load_metric("wer")
processor = Wav2Vec2Processor.from_pretrained("tanmaylaud/wav2vec2-large-xlsr-hindi-marathi")
model = Wav2Vec2ForCTC.from_pretrained("tanmaylaud/wav2vec2-large-xlsr-hindi-marathi")
model.to("cuda")
chars_to_ignore_regex = '[\\\\\\\\,\\\\\\\\?\\\\\\\\.\\\\\\\\!\\\\\\\\-\\\\\\\\;\\\\\\\\:\\\\\\\\"\\\\\\\\“\\\\\\\\%\\\\\\\\‘\\\\\\\\”\\\\\\\\�\\\\\\\\।]'
# Preprocessing the datasets.
# We need to read the audio files as arrays
def speech_file_to_array_fn(batch):
batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"])
speech_array, sampling_rate = torchaudio.load(batch["path"])
batch["speech"] = speech_array[0].numpy()
batch["sampling_rate"] = sampling_rate
batch["target_text"] = batch["sentence"]
batch["speech"] = librosa.resample(np.asarray(batch["speech"]), sampling_rate, 16_000)
batch["sampling_rate"] = 16_000
return batch
test= test.map(speech_file_to_array_fn)
# Preprocessing the datasets.
# We need to read the audio 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, group_tokens=False)
# we do not want to group tokens when computing the metrics
return batch
result = test.map(evaluate, batched=True, batch_size=32)
print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"], references=result["text"])))
```
Link to eval notebook : https://colab.research.google.com/drive/1nZRTgKfxCD9cvy90wikTHkg2il3zgcqW#scrollTo=cXWFbhb0d7DT
WER : 24.944955% (Lesser is better) |