[Bug/Model Request]: Is slower than sentence transformer for all-minilm-l6-v2

What happened?

On benchmarking synchronous computation times for generating embeddings for

1. Using sentence transformers: ~1300 msgs per sec

    from sentence_transformers import SentenceTransformer
    model_standard = SentenceTransformer("all-MiniLM-L6-v2")

    start_time = time.time()
    for i in range(iter_count):
        model_standard.encode(random.sample(sentences, 1)[0])
    time_standard = time.time() - start_time
    print("Standard requires: {}s".format(time_standard))
    print("{} processed per sec".format(batch_size*iter_count/time_standard))

VS

2. Using FastEmbed (Synchronously): 800 msgs per sec

    fast_model = TextEmbedding(model_name="sentence-transformers/all-MiniLM-L6-v2")
    start_time = time.time()
    for i in range(iter_count):
        list(fast_model.embed(random.sample(sentences, 1)[0]))
    time_standard = time.time() - start_time
    print("Fast requires: {}s".format(time_standard))
    print("{} processed per sec".format(batch_size*iter_count/time_standard))

I am using fastembed 0.3.3

pip show fastembed
Name: fastembed
Version: 0.3.3
Summary: Fast, light, accurate library built for retrieval embedding generation
Home-page: https://github.com/qdrant/fastembed
Author: Qdrant Team
Author-email: info@qdrant.tech
License: Apache License
Location: /Users/<>/PycharmProjects/Voyager/venv/lib/python3.9/site-packages
Requires: tqdm, PyStemmer, numpy, mmh3, onnxruntime, pillow, onnx, loguru, tokenizers, huggingface-hub, snowballstemmer, requests
Required-by: 

Why is this working so slow wrt original impl.? What can I do to improve performance ?

What Python version are you on? e.g. python --version

3.9.16

Version

0.2.7 (Latest)

What os are you seeing the problem on?

MacOS

Relevant stack traces and/or logs

No response

Reproduce the comparison using FastEmbed 0.3.3, Python 3.9.16 on macOS, and the all-MiniLM-L6-v2 model. Start at TextEmbedding and its synchronous embed call, compare it with SentenceTransformer.encode, and verify whether the benchmark uses equivalent inputs and batching. Done means identifying the performance difference and documenting or implementing a justified improvement.