初始化项目，由ModelHub XC社区提供模型
Model: Abdullahu5mani/flowscribe-qwen2.5-0.5b-v2 Source: Original Platform
This commit is contained in:
ModelHub XC
37
.gitattributes
vendored
Normal file
37
.gitattributes
vendored
Normal file
@@ -0,0 +1,37 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
model_q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
189
README.md
Normal file
189
README.md
Normal file
@@ -0,0 +1,189 @@
|
||||
---
|
||||
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
|
||||
- conversational
|
||||
pipeline_tag: text-generation
|
||||
datasets:
|
||||
- Abdullahu5mani/flowscribe-dataset
|
||||
---
|
||||
|
||||
# FlowScribe — Qwen2.5-0.5B Speech Transcript Formatter (v2)
|
||||
|
||||
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-v2"
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
model_id,
|
||||
torch_dtype=torch.bfloat16,
|
||||
device_map="auto"
|
||||
)
|
||||
|
||||
def format_transcript(raw_text, style="Auto"):
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are Flowscribe, an expert Speech-to-Text post-processing AI. You accurately transcribe and format 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 Flowscribe, an expert Speech-to-Text post-processing AI. You accurately transcribe and format 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 |
|
||||
|---|---|
|
||||
| Version | v2 |
|
||||
| Base model | Qwen/Qwen2.5-0.5B-Instruct |
|
||||
| Fine-tuning method | LoRA (via [Unsloth](https://github.com/unslothai/unsloth)) |
|
||||
| Parameters | ~500M (72.4% trained) |
|
||||
| Training epochs | 3 |
|
||||
| Learning rate | 2e-5 |
|
||||
| Effective batch size | 16 (batch 8 × grad accumulation 2) |
|
||||
| Sequence length | 2048 |
|
||||
| Optimizer | AdamW 8-bit |
|
||||
| Final training loss | 0.616 |
|
||||
| Training hardware | NVIDIA RTX 4070 Laptop GPU 8GB |
|
||||
| Chat template | ChatML |
|
||||
| Quantization | Q4_K_M (via llama.cpp) |
|
||||
|
||||
---
|
||||
|
||||
## Training Data
|
||||
|
||||
Trained on ~27,400 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
|
||||
|
||||
---
|
||||
|
||||
## Files
|
||||
|
||||
| File | Description |
|
||||
|---|---|
|
||||
| `model.safetensors` | Full-precision fine-tuned weights (BF16) |
|
||||
| `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)
|
||||
24
added_tokens.json
Normal file
24
added_tokens.json
Normal file
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"</tool_call>": 151658,
|
||||
"<tool_call>": 151657,
|
||||
"<|box_end|>": 151649,
|
||||
"<|box_start|>": 151648,
|
||||
"<|endoftext|>": 151643,
|
||||
"<|file_sep|>": 151664,
|
||||
"<|fim_middle|>": 151660,
|
||||
"<|fim_pad|>": 151662,
|
||||
"<|fim_prefix|>": 151659,
|
||||
"<|fim_suffix|>": 151661,
|
||||
"<|im_end|>": 151645,
|
||||
"<|im_start|>": 151644,
|
||||
"<|image_pad|>": 151655,
|
||||
"<|object_ref_end|>": 151647,
|
||||
"<|object_ref_start|>": 151646,
|
||||
"<|quad_end|>": 151651,
|
||||
"<|quad_start|>": 151650,
|
||||
"<|repo_name|>": 151663,
|
||||
"<|video_pad|>": 151656,
|
||||
"<|vision_end|>": 151653,
|
||||
"<|vision_pad|>": 151654,
|
||||
"<|vision_start|>": 151652
|
||||
}
|
||||
54
chat_template.jinja
Normal file
54
chat_template.jinja
Normal file
@@ -0,0 +1,54 @@
|
||||
{%- if tools %}
|
||||
{{- '<|im_start|>system\n' }}
|
||||
{%- if messages[0]['role'] == 'system' %}
|
||||
{{- messages[0]['content'] }}
|
||||
{%- else %}
|
||||
{{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
|
||||
{%- endif %}
|
||||
{{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
||||
{%- for tool in tools %}
|
||||
{{- "\n" }}
|
||||
{{- tool | tojson }}
|
||||
{%- endfor %}
|
||||
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
||||
{%- else %}
|
||||
{%- if messages[0]['role'] == 'system' %}
|
||||
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- for message in messages %}
|
||||
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{{- '<|im_start|>' + message.role }}
|
||||
{%- if message.content %}
|
||||
{{- '\n' + message.content }}
|
||||
{%- endif %}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- if tool_call.function is defined %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_call>\n{"name": "' }}
|
||||
{{- tool_call.name }}
|
||||
{{- '", "arguments": ' }}
|
||||
{{- tool_call.arguments | tojson }}
|
||||
{{- '}\n</tool_call>' }}
|
||||
{%- endfor %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- elif message.role == "tool" %}
|
||||
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
|
||||
{{- '<|im_start|>user' }}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_response>\n' }}
|
||||
{{- message.content }}
|
||||
{{- '\n</tool_response>' }}
|
||||
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- if add_generation_prompt %}
|
||||
{{- '<|im_start|>assistant\n' }}
|
||||
{%- endif %}
|
||||
59
config.json
Normal file
59
config.json
Normal file
@@ -0,0 +1,59 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen2ForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": null,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 151645,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 896,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 4864,
|
||||
"layer_types": [
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention"
|
||||
],
|
||||
"max_position_embeddings": 32768,
|
||||
"max_window_layers": 21,
|
||||
"model_type": "qwen2",
|
||||
"num_attention_heads": 14,
|
||||
"num_hidden_layers": 24,
|
||||
"num_key_value_heads": 2,
|
||||
"pad_token_id": 151665,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_parameters": {
|
||||
"rope_theta": 1000000.0,
|
||||
"rope_type": "default"
|
||||
},
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": true,
|
||||
"transformers_version": "5.3.0",
|
||||
"unsloth_fixed": true,
|
||||
"unsloth_version": "2026.3.18",
|
||||
"use_cache": false,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
14
generation_config.json
Normal file
14
generation_config.json
Normal file
@@ -0,0 +1,14 @@
|
||||
{
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"max_length": 32768,
|
||||
"pad_token_id": 151665,
|
||||
"repetition_penalty": 1.1,
|
||||
"temperature": 0.7,
|
||||
"top_k": 20,
|
||||
"top_p": 0.8,
|
||||
"transformers_version": "5.3.0"
|
||||
}
|
||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f727b16e77f999f83e71751fff065d807d882dc33273b38289580adb996d895a
|
||||
size 988097824
|
||||
3
model_q4_k_m.gguf
Normal file
3
model_q4_k_m.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:26655766ab6d63ef33a023eb486fb0a020aa8fbcd7041a7fdb3347127fbde5d2
|
||||
size 397807360
|
||||
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal file
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|vision_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:bd5948af71b4f56cf697f7580814c7ce8b80595ef985544efcacf716126a2e31
|
||||
size 11422356
|
||||
15
tokenizer_config.json
Normal file
15
tokenizer_config.json
Normal file
@@ -0,0 +1,15 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"backend": "tokenizers",
|
||||
"bos_token": null,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"is_local": false,
|
||||
"model_max_length": 32768,
|
||||
"pad_token": "<|PAD_TOKEN|>",
|
||||
"padding_side": "left",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user