Instructions to use pymlex/ipa-transcriptor-300M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pymlex/ipa-transcriptor-300M with Transformers:

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

pipe = pipeline("text-generation", model="pymlex/ipa-transcriptor-300M")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("pymlex/ipa-transcriptor-300M")
model = AutoModelForMultimodalLM.from_pretrained("pymlex/ipa-transcriptor-300M")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use pymlex/ipa-transcriptor-300M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pymlex/ipa-transcriptor-300M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pymlex/ipa-transcriptor-300M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/pymlex/ipa-transcriptor-300M

SGLang

How to use pymlex/ipa-transcriptor-300M 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 "pymlex/ipa-transcriptor-300M" \
    --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": "pymlex/ipa-transcriptor-300M",
		"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 "pymlex/ipa-transcriptor-300M" \
        --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": "pymlex/ipa-transcriptor-300M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use pymlex/ipa-transcriptor-300M with Docker Model Runner:
```
docker model run hf.co/pymlex/ipa-transcriptor-300M
```

ipa-transcriptor-300M / README.md

pymlex

Update README.md

28bf84e verified 13 days ago

preview code

raw

history blame contribute delete

2.13 kB

metadata

license: gpl-3.0
library_name: transformers
tags:
  - phonetics
  - ipa
  - byt5
  - seq2seq
pipeline_tag: text-generation
base_model: google/byt5-small
language:
  - en
metrics:
  - perplexity
  - bleu

IPA Transcriptor 300M

Fine-tuned google/byt5-small for English word to IPA transcription.

Task format:

ipa: analytical  ->  ˌænəˈlɪtɪkəl

Training data: English phonetic and syllable count dictionary, 125,925 word–IPA pairs after cleaning.

GitHub: pymlex/ipa-transcriptor-300M

Benchmark

Fine-tuned on NVIDIA L4, run colab_l4_bf16, beam search num_beams=4.

Metric	Validation	Test
`n_samples`	6296	6297
`loss`	0.1515	0.1478
`perplexity`	1.1636	1.1592
`token_accuracy`	0.7849	0.7858
`exact_match`	0.5982	0.6111
`char_accuracy`	0.8948	0.8969
`cer`	0.1066	0.1045
`bleu`	59.82	61.11

Dataset length distributions

Training loss

Inference

from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
import torch

model_id = "pymlex/ipa-transcriptor-300M"
source_prefix = "ipa: "

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForSeq2SeqLM.from_pretrained(model_id)
model.eval()
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model.to(device)

def transcribe(word: str, num_beams: int = 4) -> str:
    source = f"{source_prefix}{word.strip().lower()}"
    encoded = tokenizer(source, return_tensors="pt", truncation=True, max_length=36).to(device)
    output_ids = model.generate(**encoded, max_new_tokens=56, num_beams=num_beams, early_stopping=True)
    return tokenizer.decode(output_ids[0], skip_special_tokens=True)

print(transcribe("analytical"))