初始化项目，由ModelHub XC社区提供模型
Model: Abdullahu5mani/flowscribe-qwen2.5-0.5b Source: Original Platform
This commit is contained in:
ModelHub XC
187
README.md
Normal file
187
README.md
Normal file
@@ -0,0 +1,187 @@
|
||||
---
|
||||
language:
|
||||
- en
|
||||
license: mit
|
||||
base_model: Qwen/Qwen2.5-0.5B-Instruct
|
||||
tags:
|
||||
- text-generation
|
||||
- fine-tuned
|
||||
- lora
|
||||
- gguf
|
||||
- speech-to-text
|
||||
- text-cleanup
|
||||
- unsloth
|
||||
- qwen2
|
||||
pipeline_tag: text-generation
|
||||
datasets:
|
||||
- Abdullahu5mani/flowscribe-dataset
|
||||
---
|
||||
|
||||
# FlowScribe — Qwen2.5-0.5B Speech Transcript Formatter
|
||||
|
||||
A fine-tuned version of [Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct) that converts raw, messy speech-to-text output into clean, formatted text across multiple writing styles.
|
||||
|
||||
**GitHub:** [github.com/Abdullahu5mani/flowscribe](https://github.com/Abdullahu5mani/flowscribe)
|
||||
|
||||
---
|
||||
|
||||
## The Problem
|
||||
|
||||
Voice dictation tools like Whisper produce transcripts full of filler words (`um`, `uh`, `like`), self-corrections (`make it 5... no wait, 6`), and no punctuation or formatting. This model post-processes those transcripts into polished text, with awareness of the desired output style.
|
||||
|
||||
---
|
||||
|
||||
## Styles
|
||||
|
||||
| Style | Behavior |
|
||||
|---|---|
|
||||
| `Auto` | Intelligent default — removes fillers, fixes grammar, handles self-corrections, applies structure |
|
||||
| `Professional` | Formal business tone, structured layout, perfect grammar |
|
||||
| `Casual` | Keeps the speaker's voice, light cleanup, contractions preserved |
|
||||
| `Verbatim` | Preserves exact wording, only strips `um`/`uh` and applies spoken formatting commands |
|
||||
| `Software_Dev` | Formats code terms, variable names (`camelCase`, `snake_case`), technical jargon |
|
||||
| `Enthusiastic` | High energy, exclamation marks, positive phrasing |
|
||||
|
||||
---
|
||||
|
||||
## Usage
|
||||
|
||||
```python
|
||||
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."
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## GGUF (Quantized) Usage
|
||||
|
||||
A Q4_K_M quantized GGUF version is included in this repository for fast CPU/GPU inference via [llama-cpp-python](https://github.com/abetlen/llama-cpp-python).
|
||||
|
||||
```python
|
||||
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."
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Model Details
|
||||
|
||||
| Property | Value |
|
||||
|---|---|
|
||||
| Base model | Qwen/Qwen2.5-0.5B-Instruct |
|
||||
| Fine-tuning method | LoRA (via [Unsloth](https://github.com/unslothai/unsloth)) |
|
||||
| Parameters | ~500M |
|
||||
| Training epochs | 3 |
|
||||
| Learning rate | 2e-5 |
|
||||
| Effective batch size | 16 (batch 2 × grad accumulation 8) |
|
||||
| Sequence length | 2048 |
|
||||
| Optimizer | AdamW 8-bit |
|
||||
| Training hardware | NVIDIA RTX 4070 8GB VRAM |
|
||||
| Chat template | ChatML |
|
||||
| Quantization | Q4_K_M (via llama.cpp) |
|
||||
|
||||
---
|
||||
|
||||
## Training Data
|
||||
|
||||
Trained on ~19,800 synthetically generated examples from [flowscribe-dataset](https://huggingface.co/datasets/Abdullahu5mani/flowscribe-dataset).
|
||||
|
||||
Each example is an Alpaca-style JSON object:
|
||||
```json
|
||||
{
|
||||
"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."
|
||||
}
|
||||
```
|
||||
|
||||
Data was generated using Google Gemini (primary) and 16 free OpenRouter models (fallback) across 10 domain scenarios: business email, software dev, personal messages, productivity lists, medical notes, and more.
|
||||
|
||||
---
|
||||
|
||||
## Limitations
|
||||
|
||||
- Optimized for English only
|
||||
- Training data is synthetic — real-world dictation edge cases may vary
|
||||
- The 0.5B parameter size prioritizes speed and local deployment over raw capability
|
||||
- Dataset reached ~19.8K examples (target was 50K); further training on more data would improve robustness
|
||||
|
||||
---
|
||||
|
||||
## Files
|
||||
|
||||
| File | Description |
|
||||
|---|---|
|
||||
| `model.safetensors` | Full-precision fine-tuned weights |
|
||||
| `model_q4_k_m.gguf` | Q4_K_M quantized GGUF for llama.cpp |
|
||||
| `config.json` | Model configuration |
|
||||
| `tokenizer.json` | Tokenizer |
|
||||
| `chat_template.jinja` | ChatML chat template |
|
||||
|
||||
---
|
||||
|
||||
## License
|
||||
|
||||
MIT — see [LICENSE](https://github.com/Abdullahu5mani/flowscribe/blob/main/LICENSE)
|
||||
Reference in New Issue
Block a user