metadata
library_name: transformers
language:
- fa
license: apache-2.0
base_model: openai/whisper-medium
tags:
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_17_0
model-index:
- name: Whisper medium Fa - Common Voice
results: []
Whisper medium Fa - Common Voice
This model is a fine-tuned version of openai/whisper-medium on the Common Voice 17.0 dataset.
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Test results
- Best test WER (Word Error Rate): 0.322
- Best test CER (Character Error Rate): 0.106
Usage
import torch
from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
device = "cuda:0" if torch.cuda.is_available() else "cpu"
torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
model_id = "aictsharif/whisper-medium-fa"
model = AutoModelForSpeechSeq2Seq.from_pretrained(
model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True, 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,
torch_dtype=torch_dtype,
device=device,
)
result = pipe('sample.mp3')
print(result["text"])
Framework versions
- Transformers 4.51.3
- Pytorch 2.5.1+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1