Instructions to use Akash-Sakala/flan-t5-large-transcript-formatter with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Akash-Sakala/flan-t5-large-transcript-formatter with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Akash-Sakala/flan-t5-large-transcript-formatter")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("Akash-Sakala/flan-t5-large-transcript-formatter")
model = AutoModelForSeq2SeqLM.from_pretrained("Akash-Sakala/flan-t5-large-transcript-formatter")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Akash-Sakala/flan-t5-large-transcript-formatter with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Akash-Sakala/flan-t5-large-transcript-formatter"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Akash-Sakala/flan-t5-large-transcript-formatter",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Akash-Sakala/flan-t5-large-transcript-formatter

SGLang

How to use Akash-Sakala/flan-t5-large-transcript-formatter 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 "Akash-Sakala/flan-t5-large-transcript-formatter" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Akash-Sakala/flan-t5-large-transcript-formatter",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "Akash-Sakala/flan-t5-large-transcript-formatter" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Akash-Sakala/flan-t5-large-transcript-formatter",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Akash-Sakala/flan-t5-large-transcript-formatter with Docker Model Runner:
```
docker model run hf.co/Akash-Sakala/flan-t5-large-transcript-formatter
```

flan-t5-large-transcript-formatter / README.md

Akash-Sakala

Distilled Flan-T5-Large transcript formatter + model card

8664291 verified 14 days ago

preview code

Raw

History Blame Contribute Delete

2.63 kB

metadata

license: apache-2.0
language:
  - en
base_model: google/flan-t5-large
pipeline_tag: text2text-generation
library_name: transformers
tags:
  - speech-to-text
  - transcript-formatting
  - asr-post-processing
  - dictation
  - knowledge-distillation

Flan-T5-Large Transcript Formatter (distilled, < 1 GB target)

Raw speech-to-text transcript in → clean, formatted transcript out (punctuation, casing, filler/disfluency removal, ITN, homophones, proper nouns, URLs/emails, and layout). The model takes the raw transcript as its only input (no system prompt) and emits the formatted transcript.

Distillation

Teacher: GPT-OSS-120B → Phase-1 distilled GPT-OSS-20B formatter, which reproduces the L0–L5 + RL curriculum behaviour at ~99.5% adjusted accuracy.
Student: google/flan-t5-large (783M, encoder–decoder).
Method: off-policy / sequence-level knowledge distillation (prompt distillation). Trained on (raw → formatted) pairs using the curriculum gold targets (cleaner than propagating the teacher's residual errors).

Data

Sampled from the layered curriculum (L0–L5 + RL), de-duplicated latest-layer-wins, with the per-layer val splits held out and made disjoint from train: 18,129 train / 2,713 validation pairs, 21 formatting categories.

Training


Hardware	1× RTX 5090 (32 GB), bf16
Optimizer	Adafactor, lr 1e-4, warmup_ratio 0.03
Batch	8 × grad-accum 2 = effective 16
Seq length	max 640 tokens (covers the longest pair, 552 tok; zero truncation)
Regularization	gradient checkpointing; early stopping (patience 3), best-checkpoint by val loss
Result	best val loss 0.005784 @ step 2250 (~epoch 2.0); early-stopped at step 3000

Usage

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
tok = AutoTokenizer.from_pretrained("Akash-Sakala/flan-t5-large-transcript-formatter")
model = AutoModelForSeq2SeqLM.from_pretrained("Akash-Sakala/flan-t5-large-transcript-formatter")
raw = "i went to the the store yesterday it was closed so i couldnt get the milk"
ids = tok(raw, return_tensors="pt")
print(tok.decode(model.generate(**ids, max_new_tokens=640, num_beams=1)[0], skip_special_tokens=True))

Limitations

A 783M student shows a capacity step-down from the 20B teacher on the hardest L4 layout cases (long email/list blocks); T5 was pretrained mostly at 512 tokens. For an int8, CPU-only deployment (< 1 GB) convert with CTranslate2.

License Apache-2.0 (matches the openai/gpt-oss base and the curriculum dataset).