Text Generation
Transformers
Safetensors
English
gemma4_text
transcript-cleanup
meetings
asr-post-processing
disfluency-removal
conversational
Instructions to use xav-ie/scribe-cleanup with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use xav-ie/scribe-cleanup with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="xav-ie/scribe-cleanup") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("xav-ie/scribe-cleanup") model = AutoModelForCausalLM.from_pretrained("xav-ie/scribe-cleanup", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use xav-ie/scribe-cleanup with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "xav-ie/scribe-cleanup" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "xav-ie/scribe-cleanup", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/xav-ie/scribe-cleanup
- SGLang
How to use xav-ie/scribe-cleanup with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "xav-ie/scribe-cleanup" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "xav-ie/scribe-cleanup", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "xav-ie/scribe-cleanup" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "xav-ie/scribe-cleanup", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use xav-ie/scribe-cleanup with Docker Model Runner:
docker model run hf.co/xav-ie/scribe-cleanup
|
Download COMPARISON.md from xav-ie/scribe-cleanup: direct link, hf CLI and curl.
- Browser
- Download file 6.78 kB
-
https://huggingface.co/xav-ie/scribe-cleanup/resolve/main/COMPARISON.md
- Command line
-
hf download hf://xav-ie/scribe-cleanup/COMPARISON.md
-
curl -L -o COMPARISON.md https://huggingface.co/xav-ie/scribe-cleanup/resolve/main/COMPARISON.md
6.78 kB
| # How scribe cleanup compares | |
| Given the same meeting transcript, which small model on your own computer cleans it best without changing what was | |
| said? | |
| In short: scribe cleanup makes the fewest errors and drops 0.5% of real words; the dictation models drop 4.5% to 15.5%, and lose a "not" in 1.8% to 29.1% of meeting chunks. | |
| **What was compared.** Every released open transcript-cleanup model we found that is small enough for a laptop, plus | |
| two simple baselines: | |
| - **Raw transcript:** the speech-to-text output, untouched. | |
| - **Rules only:** a simple script that deletes ums and repeated words. | |
| - **Stock Gemma 4 E2B:** scribe cleanup's starting model without our training, given detailed instructions instead. | |
| It shows what the training adds. | |
| - **Simplewords, Boswell, Spokenly and Sotto:** cleanup models built for dictation, where one person dictates one | |
| sentence at a time. Each meeting line was sent to them on its own, with each model's own instructions. Boswell's | |
| page says it is meant to run inside its Mac app, so it got the instructions that app sends. | |
| Size is the number of learned values in a model, in billions (B); bigger usually means slower. Each model takes hours | |
| to run, so all of them ran on every third chunk of the tests; that is why the numbers differ slightly from the model | |
| card, which uses every chunk. Scores are each model's own output, before any safety check, and | |
| [METHODOLOGY.md](METHODOLOGY.md#scoring) explains them. | |
| <img src="diagrams/quality.svg#hf-light-mode-only" alt="Errors in words, punctuation and capitals on meetings (lower is better): Raw transcript 23.1%, Rules only 20.8%, Stock Gemma 4 E2B 23.7%, scribe cleanup v1 13.4%, Simplewords v2 29.6%, Boswell 37.2%, Spokenly Cleanup 1 26.5%, Sotto 29.6%"> | |
| <img src="diagrams/quality-dark.svg#hf-dark-mode-only" alt="Errors in words, punctuation and capitals on meetings (lower is better): Raw transcript 23.1%, Rules only 20.8%, Stock Gemma 4 E2B 23.7%, scribe cleanup v1 13.4%, Simplewords v2 29.6%, Boswell 37.2%, Spokenly Cleanup 1 26.5%, Sotto 29.6%"> | |
| <img src="diagrams/losses.svg#hf-light-mode-only" alt="Real words dropped: Stock Gemma 4 E2B 2.1%, scribe cleanup v1 0.5%, Simplewords v2 11.4%, Boswell 15.5%, Spokenly Cleanup 1 4.5%, Sotto 8.5%; Chunks where a "not" went missing: Stock Gemma 4 E2B 0%, scribe cleanup v1 0%, Simplewords v2 29.1%, Boswell 22.7%, Spokenly Cleanup 1 1.8%, Sotto 10.9%; Chunks with a wrong number (number tests): Stock Gemma 4 E2B 13.1%, scribe cleanup v1 1.8%, Simplewords v2 41.2%, Boswell 74.2%, Spokenly Cleanup 1 56.6%, Sotto 76%"> | |
| <img src="diagrams/losses-dark.svg#hf-dark-mode-only" alt="Real words dropped: Stock Gemma 4 E2B 2.1%, scribe cleanup v1 0.5%, Simplewords v2 11.4%, Boswell 15.5%, Spokenly Cleanup 1 4.5%, Sotto 8.5%; Chunks where a "not" went missing: Stock Gemma 4 E2B 0%, scribe cleanup v1 0%, Simplewords v2 29.1%, Boswell 22.7%, Spokenly Cleanup 1 1.8%, Sotto 10.9%; Chunks with a wrong number (number tests): Stock Gemma 4 E2B 13.1%, scribe cleanup v1 1.8%, Simplewords v2 41.2%, Boswell 74.2%, Spokenly Cleanup 1 56.6%, Sotto 76%"> | |
| **How clean the result is, on meetings** (110 chunks; for every score, see [the definitions](METHODOLOGY.md#scoring)) | |
| | System | Size | Word errors | Word, punctuation and capital errors | Punctuation (0 to 1) | Capitals (0 to 1) | Filler removal (0 to 1) | | |
| |---|---|---|---|---|---|---| | |
| | Raw transcript | | 6.7% | 23.1% | 0.23 | 0.53 | n/a | | |
| | Rules only (drop fillers and repeats) | | 2.7% | 20.8% | 0.23 | 0.59 | 0.76 | | |
| | Stock Gemma 4 E2B (with a detailed prompt) | 2B | 5.3% | 23.7% | 0.20 | 0.48 | 0.60 | | |
| | **scribe cleanup v1** | 2B | 1.3% | 13.4% | 0.58 | 0.78 | 0.88 | | |
| | [Simplewords v2](https://huggingface.co/ReFyneLabs/simplewords-dictation-cleanup-v2) | 2B | 16% | 29.6% | 0.46 | 0.62 | 0.41 | | |
| | [Boswell](https://huggingface.co/meetboswell/boswell-dictation-cleanup) | 1.7B | 23% | 37.2% | 0.40 | 0.62 | 0.26 | | |
| | [Spokenly Cleanup 1](https://huggingface.co/spokenly/cleanup-1) | 0.6B | 9.6% | 26.5% | 0.41 | 0.62 | 0.56 | | |
| | [Sotto](https://huggingface.co/juanquivilla/sotto-cleanup-lfm25-350m) | 0.35B | 14.3% | 29.6% | 0.41 | 0.61 | 0.47 | | |
| **What gets lost** (meetings: 110 chunks; number tests: 221 chunks) | |
| | System | Real words dropped | Missing "not" | Wrong number | Wrong number (number tests) | Unsure number converted (number tests) | Correction not applied (number tests) | Lines kept intact | | |
| |---|---|---|---|---|---|---|---| | |
| | Stock Gemma 4 E2B (with a detailed prompt) | 2.1% | 0% | 4.5% | 13.1% | 3.6% | 30.3% | 92.7% | | |
| | **scribe cleanup v1** | 0.5% | 0% | 2.7% | 1.8% | 0% | 0% | 99.1% | | |
| | [Simplewords v2](https://huggingface.co/ReFyneLabs/simplewords-dictation-cleanup-v2) | 11.4% | 29.1% | 23.6% | 41.2% | 0.4% | 0% | n/a (one line at a time) | | |
| | [Boswell](https://huggingface.co/meetboswell/boswell-dictation-cleanup) | 15.5% | 22.7% | 36.4% | 74.2% | 0% | 0% | n/a (one line at a time) | | |
| | [Spokenly Cleanup 1](https://huggingface.co/spokenly/cleanup-1) | 4.5% | 1.8% | 11.8% | 56.6% | 38.9% | 0.4% | n/a (one line at a time) | | |
| | [Sotto](https://huggingface.co/juanquivilla/sotto-cleanup-lfm25-350m) | 8.5% | 10.9% | 24.6% | 76% | 29% | 2.7% | n/a (one line at a time) | | |
| **Why the dictation models lose meaning.** They were built to polish one dictated sentence, so on messy meeting speech | |
| they rewrite: they invent endings, drop the half of a sentence that says "not", and guess what an unclear number | |
| meant. Real outputs from the tests, with the changed part in bold: | |
| | Model | What went wrong | Heard | The model wrote | scribe cleanup wrote | | |
| |---|---|---|---|---| | |
| | Boswell | invented an ending | yeah and I think today there | Yeah and I think today there **is no way we finish the report by Friday.** | Yeah. And I think today there | | |
| | Boswell | invented a number | the next channel in the numeric pattern or no swapping | The next channel in the numeric pattern **is: 12.** | The next channel in the numeric pattern or? No swapping. | | |
| | Simplewords v2 | dropped the "don't" half | we do want drop-down we don't want them to type them do we | We do want drop-downs. | We do want drop-down. We don't want them to type them, do we? | | |
| | Simplewords v2 | dropped the "didn't" | did and some classes didn't yeah | Did some classes. | did and some classes didn't. Yeah. | | |
| | Sotto | changed a number | the target was fourteen fifty I think | The target was **146**. | The target was fourteen fifty I think. | | |
| | Spokenly Cleanup 1 | guessed a time | we can regroup at half past eight | We can regroup at **18:30**. | We can regroup at half past eight. | | |
| The first four are real meeting lines; the last two are made-up lines from the number tests. None of this ranks these | |
| models at dictation, the job they were built for. | |