Abdullahu5mani/flowscribe-qwen2.5-0.5b

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "Abdullahu5mani/flowscribe-qwen2.5-0.5b"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.float16,
    device_map="auto"
)

def format_transcript(raw_text, style="Auto"):
    messages = [
        {
            "role": "system",
            "content": "You are a helpful assistant that transcribes and formats text based on a specific style instruction."
        },
        {
            "role": "user",
            "content": f"Transcribe and format this with style: {style}\nInput: {raw_text}"
        }
    ]
    text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = tokenizer([text], return_tensors="pt").to(model.device)
    outputs = model.generate(**inputs, max_new_tokens=512, do_sample=False)
    output_ids = outputs[0][len(inputs.input_ids[0]):]
    return tokenizer.decode(output_ids, skip_special_tokens=True)

# Examples
print(format_transcript(
    "um so the meeting is at 5... no wait make it 6 and uh we need to discuss the q3 budget",
    style="Professional"
))
# → "The meeting is at 6 PM to discuss the Q3 budget."

print(format_transcript(
    "the api endpoint is slash api slash users new line it takes a POST request with JSON",
    style="Software_Dev"
))
# → "The API endpoint is `/api/users`\nIt takes a POST request with JSON."

from llama_cpp import Llama

llm = Llama(
    model_path="model_q4_k_m.gguf",
    n_ctx=2048,
    n_gpu_layers=-1,   # Set to 0 for CPU-only
    verbose=False
)

response = llm.create_chat_completion(
    messages=[
        {
            "role": "system",
            "content": "You are a helpful assistant that transcribes and formats text based on a specific style instruction."
        },
        {
            "role": "user",
            "content": "Transcribe and format this with style: Casual\nInput: hey um so i was thinking we could like grab lunch tomorrow you know around noon ish"
        }
    ],
    max_tokens=256,
    temperature=0.1,
)
print(response["choices"][0]["message"]["content"])
# → "Hey, I was thinking we could grab lunch tomorrow around noon."

{
  "instruction": "Transcribe and format this with style: Professional",
  "input": "um so like the uh proposal is due friday and we need to finalize the, i mean confirm the budget",
  "output": "The proposal is due Friday and we need to confirm the budget."
}