metadata

language:
  - ar
license: apache-2.0
base_model: openai/whisper-large-v3
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - Voice_Cleverlytics
model-index:
  - name: Whisper_Cleverlytics
    results: []
metrics:
  - wer

Whisper_Cleverlytics

Usage

To run the model, first install the Transformers library through the GitHub repo.

pip install --upgrade pip
pip install --upgrade git+https://github.com/huggingface/transformers.git accelerate datasets[audio]

import torch
from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
#from datasets import load_dataset

device = "cuda:0" if torch.cuda.is_available() else "cpu"
torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
model_id = "smerchi/Arabic-Morocco-Speech_To_Text"

model = AutoModelForSpeechSeq2Seq.from_pretrained(
    model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=False, use_safetensors=True
)
model.to(device)

processor = AutoProcessor.from_pretrained(model_id)

pipe = pipeline(
    "automatic-speech-recognition",
    model=model,
    tokenizer=processor.tokenizer,
    feature_extractor=processor.feature_extractor,
    max_new_tokens=128,
    chunk_length_s=30,
    batch_size=16,
    return_timestamps=True,
    torch_dtype=torch_dtype,
    device=device,
)

audio="/content/audio.mp3"

%time result = pipe(audio)
print(result["text"],)

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 1e-05
num_epochs: 20

Training results

Framework versions

Transformers 4.35.2
Pytorch 2.0.1+cu117
Datasets 2.16.0
Tokenizers 0.14.1