Text Generation
Transformers
Safetensors
English
lfm2
transcript-cleanup
text-normalization
inverse-text-normalization
punctuation
dictation
conversational
Instructions to use scribekey/scribekey-cleanup-fast with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use scribekey/scribekey-cleanup-fast with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="scribekey/scribekey-cleanup-fast") 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("scribekey/scribekey-cleanup-fast") model = AutoModelForCausalLM.from_pretrained("scribekey/scribekey-cleanup-fast", 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 scribekey/scribekey-cleanup-fast with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "scribekey/scribekey-cleanup-fast" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "scribekey/scribekey-cleanup-fast", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/scribekey/scribekey-cleanup-fast
- SGLang
How to use scribekey/scribekey-cleanup-fast 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 "scribekey/scribekey-cleanup-fast" \ --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": "scribekey/scribekey-cleanup-fast", "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 "scribekey/scribekey-cleanup-fast" \ --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": "scribekey/scribekey-cleanup-fast", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use scribekey/scribekey-cleanup-fast with Docker Model Runner:
docker model run hf.co/scribekey/scribekey-cleanup-fast
Publish v1 card
Browse files- README.md +4 -4
- SHA256SUMS +1 -1
README.md
CHANGED
|
@@ -25,7 +25,7 @@ datasets:
|
|
| 25 |
|
| 26 |
A 350M-class English text model for cleaning speech-to-text transcripts on a device. It removes fillers and repetitions, applies spoken corrections, and adjusts punctuation, casing and layout using a control line. It takes **text**, not audio. It is a dedicated cleanup model, not a general assistant.
|
| 27 |
|
| 28 |
-
**
|
| 29 |
|
| 30 |
## Model overview
|
| 31 |
|
|
@@ -51,7 +51,7 @@ import torch
|
|
| 51 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 52 |
|
| 53 |
MODEL = "scribekey/scribekey-cleanup-fast"
|
| 54 |
-
REVISION = "v1
|
| 55 |
|
| 56 |
tokenizer = AutoTokenizer.from_pretrained(MODEL, revision=REVISION)
|
| 57 |
model = AutoModelForCausalLM.from_pretrained(
|
|
@@ -145,7 +145,7 @@ The following are **Q8_0 results at the ScribeKey app boundary**, not a BF16 ben
|
|
| 145 |
|
| 146 |
The intervals do not establish superiority over Sotto or equivalence to S1-mini. The candidate met the experiment's provisional non-regression criteria; the broader release bar remains unresolved. These values are specific benchmark metrics, not universal accuracy rates. The new-value rate is a real limitation: check names, dates, amounts, negations and important details before using the output. Keep a recoverable raw transcript.
|
| 147 |
|
| 148 |
-
Phone results often quoted for this family are for **the preceding `v7-replay` artifact**, not this package: S25 Ultra long-input warm p50/p95 1,696/2,101 ms, short-input 156/178 ms, peak combined PSS 1,567 MiB on the measured app/ASR build. They are context, not final-artifact performance claims. Midrange performance and a minimum-device guarantee are unverified.
|
| 149 |
|
| 150 |
## Training and provenance
|
| 151 |
|
|
@@ -180,4 +180,4 @@ Some training sources carry CC BY or CC BY-SA licences. They are credited separa
|
|
| 180 |
}
|
| 181 |
```
|
| 182 |
|
| 183 |
-
The `v1-rc1-attribution`
|
|
|
|
| 25 |
|
| 26 |
A 350M-class English text model for cleaning speech-to-text transcripts on a device. It removes fillers and repetitions, applies spoken corrections, and adjusts punctuation, casing and layout using a control line. It takes **text**, not audio. It is a dedicated cleanup model, not a general assistant.
|
| 27 |
|
| 28 |
+
**Release `v1`** (experiment `v7-replay-tgt`). ScribeKey Fast is ScribeKey's on-device cleanup model, replacing Sotto. The Q8_0 has offline evaluation and a direct-helper S25 Ultra check of this exact artifact (short p50/p95 155/178 ms; long 1,702/2,718 ms with Parakeet resident); midrange and product end-to-end performance have not been measured. Two public-input BF16 CPU smoke cases also ran twice with identical outputs (`bf16-smoke.json`); this is an inference check, not a BF16 quality benchmark.
|
| 29 |
|
| 30 |
## Model overview
|
| 31 |
|
|
|
|
| 51 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 52 |
|
| 53 |
MODEL = "scribekey/scribekey-cleanup-fast"
|
| 54 |
+
REVISION = "v1" # Pin the commit SHA for a deployment.
|
| 55 |
|
| 56 |
tokenizer = AutoTokenizer.from_pretrained(MODEL, revision=REVISION)
|
| 57 |
model = AutoModelForCausalLM.from_pretrained(
|
|
|
|
| 145 |
|
| 146 |
The intervals do not establish superiority over Sotto or equivalence to S1-mini. The candidate met the experiment's provisional non-regression criteria; the broader release bar remains unresolved. These values are specific benchmark metrics, not universal accuracy rates. The new-value rate is a real limitation: check names, dates, amounts, negations and important details before using the output. Keep a recoverable raw transcript.
|
| 147 |
|
| 148 |
+
Phone results often quoted for this family are for **the preceding `v7-replay` artifact**, not this package: S25 Ultra long-input warm p50/p95 1,696/2,101 ms, short-input 156/178 ms, peak combined PSS 1,567 MiB on the measured app/ASR build. They are context, not final-artifact performance claims. Midrange performance and a minimum-device guarantee are unverified. ScribeKey's catalogue keeps a conservative 6 GB device-memory floor.
|
| 149 |
|
| 150 |
## Training and provenance
|
| 151 |
|
|
|
|
| 180 |
}
|
| 181 |
```
|
| 182 |
|
| 183 |
+
The `v1` release is the public `v1-rc1-attribution` package with updated card wording; weight bytes, terms and prompt/runtime controls are unchanged from `v1-rc1`. The original RC tags are preserved.
|
SHA256SUMS
CHANGED
|
@@ -2,7 +2,7 @@
|
|
| 2 |
4d28ca14dedc0b3d0fcc2b3339f0e79931faa33874f3d24f522183a8fc70068c LICENSE
|
| 3 |
09dfb7155ec9f316cd19e2cf68b818b04344be000e44f29d7779cd200743337c MODIFICATIONS.md
|
| 4 |
4d0d40d15ca51c17c0d9b61ed5a0f9c06ed3640a106ae20cfea4a8f36cd02b73 NOTICE
|
| 5 |
-
|
| 6 |
75ba5b790d851b4d8084fbd0eb8624cfd3eb154bc5182fbb2c81b91ef0aea948 bf16-smoke.json
|
| 7 |
d0ca71c262852fd7020e4f77e7f424daddbe052637a05fbe63e50a2b16980c25 chat_template.jinja
|
| 8 |
13ab9863955d2016c32417ff97b1a9840951d2481b6d3095f7ae98d10611a7d2 config.json
|
|
|
|
| 2 |
4d28ca14dedc0b3d0fcc2b3339f0e79931faa33874f3d24f522183a8fc70068c LICENSE
|
| 3 |
09dfb7155ec9f316cd19e2cf68b818b04344be000e44f29d7779cd200743337c MODIFICATIONS.md
|
| 4 |
4d0d40d15ca51c17c0d9b61ed5a0f9c06ed3640a106ae20cfea4a8f36cd02b73 NOTICE
|
| 5 |
+
e3fffa6fa8c673148e5d7db9ca5fea2ed90428bb950a11d42aaf436e22011d9b README.md
|
| 6 |
75ba5b790d851b4d8084fbd0eb8624cfd3eb154bc5182fbb2c81b91ef0aea948 bf16-smoke.json
|
| 7 |
d0ca71c262852fd7020e4f77e7f424daddbe052637a05fbe63e50a2b16980c25 chat_template.jinja
|
| 8 |
13ab9863955d2016c32417ff97b1a9840951d2481b6d3095f7ae98d10611a7d2 config.json
|