Text Generation
Transformers
PyTorch
Russian
t5
text2text-generation
text
PyTorch
Transformers
text-generation-inference
Instructions to use bond005/ruT5-ASR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bond005/ruT5-ASR with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="bond005/ruT5-ASR")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("bond005/ruT5-ASR") model = AutoModelForSeq2SeqLM.from_pretrained("bond005/ruT5-ASR", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use bond005/ruT5-ASR with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "bond005/ruT5-ASR" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "bond005/ruT5-ASR", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/bond005/ruT5-ASR
- SGLang
How to use bond005/ruT5-ASR 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 "bond005/ruT5-ASR" \ --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": "bond005/ruT5-ASR", "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 "bond005/ruT5-ASR" \ --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": "bond005/ruT5-ASR", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use bond005/ruT5-ASR with Docker Model Runner:
docker model run hf.co/bond005/ruT5-ASR
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,16 @@
|
|
| 1 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
language: ru
|
| 2 |
+
datasets:
|
| 3 |
+
- SberDevices/Golos
|
| 4 |
+
- bond005/sova_rudevices
|
| 5 |
+
metrics:
|
| 6 |
+
- wer
|
| 7 |
+
- cer
|
| 8 |
+
tags:
|
| 9 |
+
- audio
|
| 10 |
+
- automatic-speech-recognition
|
| 11 |
+
- speech
|
| 12 |
license: apache-2.0
|
| 13 |
+
widget:
|
| 14 |
+
- text: уласны в москве интерне только в большом году что лепровели
|
| 15 |
+
model-index:
|
| 16 |
+
- name: ruT5-ASR for auto-correction of Russian ASR output by Ivan Bondarenko
|