File size: 3,948 Bytes
863a64d cb7ac4f aafdd3b cb7ac4f aafdd3b cb7ac4f aafdd3b cb7ac4f |
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 |
---
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: 60.80
---
# Wav2Vec2-Large-XLSR-53-Hindi-Marathi
### Fine-tuned facebook/wav2vec2-large-xlsr-53 on Hindi and Marathi using the OpenSLR SLR64 datasets. Note that this data OpenSLR contains only female voices. Please keep this in mind before using the model for your task. 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:
```
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.
```
```
import torch
import torchaudio
import librosa
from datasets import load_dataset, load_metric
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
import re
# test_data = #TODO: WRITE YOUR CODE TO LOAD THE TEST DATASET. For sample see the Colab link in Training Section.
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["text"] = re.sub(chars_to_ignore_regex, '', batch["text"]).lower()
speech_array, sampling_rate = torchaudio.load(batch["audio_path"])
batch["speech"] = librosa.resample(speech_array[0].numpy(), sampling_rate, 16_000)
return batch
test_data= test_data.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)
return batch
result = test_data.map(evaluate, batched=True, batch_size=8)
print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"], references=result["text"])))
``` |