---
language: fa
datasets:
- common_voice_6_1
tags:
- audio
- automatic-speech-recognition
license: apache-2.0
#widget:
#- example_title: Librispeech sample 1
#  src: https://cdn-media.huggingface.co/speech_samples/sample1.flac
#- example_title: Librispeech sample 2
#  src: https://cdn-media.huggingface.co/speech_samples/sample2.flac
model-index:
- name: Sharif-wav2vec2
  results:
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: Common Voice Corpus 6.1 (clean)
      type: common_voice_6_1
      config: clean
      split: test
      args: 
        language: fa
    metrics:
    - name: Test WER
      type: wer
      value: 6.0
  #- task:
   #   name: Automatic Speech Recognition
   #   type: automatic-speech-recognition
   # dataset:
   #   name: LibriSpeech (other)
   #   type: librispeech_asr
   #   config: other
   #   split: test
   #   args: 
   #     language: en
   # metrics:
   # - name: Test WER
   #   type: wer
   #   value: 8.6
---

# Sharif-wav2vec2

Prior to the usage, you may need to install the below dependencies:

```shell
pip -q install pyctcdecode
python -m pip -q install pypi-kenlm
```

Then you can use it with:
```python
import tensorflow
import torchaudio
import torch
import librosa
import numpy as np
from transformers import AutoProcessor, AutoModelForCTC

processor = AutoProcessor.from_pretrained("SLPL/Sharif-wav2vec2")
model = AutoModelForCTC.from_pretrained("SLPL/Sharif-wav2vec2")




speech_array, sampling_rate = torchaudio.load("test.wav")
speech_array = speech_array.squeeze().numpy()
speech_array = librosa.resample(
    np.asarray(speech_array),
    sampling_rate,
    processor.feature_extractor.sampling_rate)


features = processor(
    speech_array,
    sampling_rate=processor.feature_extractor.sampling_rate,
    return_tensors="pt",
    padding=True)
input_values = features.input_values
attention_mask = features.attention_mask
with torch.no_grad():
    logits = model(input_values, attention_mask=attention_mask).logits
    prediction = processor.batch_decode(logits.numpy()).text

print(prediction[0])
# تست
```

The base model fine-tuned on 108 hours of Commonvoice on 16kHz sampled speech audio. When using the model
make sure that your speech input is also sampled at 16Khz.

# Authors: Alexei Baevski, Henry Zhou, Abdelrahman Mohamed, Michael Auli

# **Abstract**

<!--
We show for the first time that learning powerful representations from speech audio alone followed by fine-tuning on transcribed speech can outperform the best semi-supervised methods while being conceptually simpler. wav2vec 2.0 masks the speech input in the latent space and solves a contrastive task defined over a quantization of the latent representations which are jointly learned. Experiments using all labeled data of Librispeech achieve 1.8/3.3 WER on the clean/other test sets. When lowering the amount of labeled data to one hour, wav2vec 2.0 outperforms the previous state of the art on the 100 hour subset while using 100 times less labeled data. Using just ten minutes of labeled data and pre-training on 53k hours of unlabeled data still achieves 4.8/8.2 WER. This demonstrates the feasibility of speech recognition with limited amounts of labeled data.
 -->

The original model can be found under https://github.com/pytorch/fairseq/tree/master/examples/wav2vec#wav2vec-20.


# Usage

To transcribe Persian audio files the model can be used as a standalone acoustic model as follows:

```python
 from transformers import Wav2Vec2Processor, Wav2Vec2ForCTC
 from datasets import load_dataset
 import torch
 
 # load model and tokenizer
 processor = Wav2Vec2Processor.from_pretrained("SLPL/Sharif-wav2vec2")
 model = Wav2Vec2ForCTC.from_pretrained("SLPL/Sharif-wav2vec2")
     
 # load dummy dataset and read soundfiles
# ds = load_dataset("patrickvonplaten/librispeech_asr_dummy", "clean", split="validation")
 
 # tokenize
 input_values = processor(ds[0]["audio"]["array"], return_tensors="pt", padding="longest").input_values  # Batch size 1
 
 # retrieve logits
 logits = model(input_values).logits
 
 # take argmax and decode
 predicted_ids = torch.argmax(logits, dim=-1)
 transcription = processor.batch_decode(predicted_ids)
 ```
 
 ## Evaluation
 
 This code snippet shows how to evaluate **facebook/wav2vec2-base-960h** on LibriSpeech's "clean" and "other" test data.
 
```python
from datasets import load_dataset
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
import torch
from jiwer import wer


librispeech_eval = load_dataset("librispeech_asr", "clean", split="test")

model = Wav2Vec2ForCTC.from_pretrained("facebook/wav2vec2-base-960h").to("cuda")
processor = Wav2Vec2Processor.from_pretrained("facebook/wav2vec2-base-960h")

def map_to_pred(batch):
    input_values = processor(batch["audio"]["array"], return_tensors="pt", padding="longest").input_values
    with torch.no_grad():
        logits = model(input_values.to("cuda")).logits

    predicted_ids = torch.argmax(logits, dim=-1)
    transcription = processor.batch_decode(predicted_ids)
    batch["transcription"] = transcription
    return batch

result = librispeech_eval.map(map_to_pred, batched=True, batch_size=1, remove_columns=["audio"])

print("WER:", wer(result["text"], result["transcription"]))
```

*Result (WER)*:

| "clean" | "other" |
|---|---|
| 3.4 | 8.6 |