distil-large-v3

1.3M
348
2 languages
FP32
license:mit
by
distil-whisper
Audio Model
OTHER
High
1.3M downloads
Battle-tested
Try on Hugging FaceAdd to Compare
Edge AI:
Mobile
Laptop
Server
Unknown
Mobile
Laptop
Server
Quick Summary

--- language: - en license: mit library_name: transformers tags: - audio - automatic-speech-recognition - transformers.

Code Examples

bash
pip install --upgrade pip
pip install --upgrade transformers accelerate datasets[audio]
bash
pip install --upgrade pip
pip install --upgrade transformers accelerate datasets[audio]
text
pip install flash-attn --no-build-isolation
text
pip install flash-attn --no-build-isolation
text
git clone https://github.com/ggerganov/whisper.cpp.git
cd whisper.cpp
text
git clone https://github.com/ggerganov/whisper.cpp.git
cd whisper.cpp
bash
pip install --upgrade huggingface_hub
bash
pip install --upgrade huggingface_hub
python
from huggingface_hub import hf_hub_download

hf_hub_download(repo_id='distil-whisper/distil-large-v3-ggml', filename='ggml-distil-large-v3.bin', local_dir='./models')
python
from huggingface_hub import hf_hub_download

hf_hub_download(repo_id='distil-whisper/distil-large-v3-ggml', filename='ggml-distil-large-v3.bin', local_dir='./models')
bash
pip install --upgrade pip
pip install --upgrade git+https://github.com/SYSTRAN/faster-whisper datasets[audio]
bash
pip install --upgrade pip
pip install --upgrade git+https://github.com/SYSTRAN/faster-whisper datasets[audio]
bash
pip install --upgrade pip
pip install --upgrade openai-whisper datasets[audio]
bash
pip install --upgrade pip
pip install --upgrade openai-whisper datasets[audio]
python
from huggingface_hub import hf_hub_download
from datasets import load_dataset
from whisper import load_model, transcribe

model_path = hf_hub_download(repo_id="distil-whisper/distil-large-v3-openai", filename="model.bin")
model = load_model(model_path)

dataset = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
sample = dataset[0]["audio"]["path"]

pred_out = transcribe(model, audio=sample, language="en")
print(pred_out["text"])
python
from huggingface_hub import hf_hub_download
from datasets import load_dataset
from whisper import load_model, transcribe

model_path = hf_hub_download(repo_id="distil-whisper/distil-large-v3-openai", filename="model.bin")
model = load_model(model_path)

dataset = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
sample = dataset[0]["audio"]["path"]

pred_out = transcribe(model, audio=sample, language="en")
print(pred_out["text"])
bash
npm i @xenova/transformers
bash
npm i @xenova/transformers
javascript
import { pipeline } from '@xenova/transformers';

const transcriber = await pipeline('automatic-speech-recognition', 'distil-whisper/distil-large-v3');

const url = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/jfk.wav';
const output = await transcriber(url);
// { text: " And so, my fellow Americans, ask not what your country can do for you. Ask what you can do for your country." }
javascript
import { pipeline } from '@xenova/transformers';

const transcriber = await pipeline('automatic-speech-recognition', 'distil-whisper/distil-large-v3');

const url = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/jfk.wav';
const output = await transcriber(url);
// { text: " And so, my fellow Americans, ask not what your country can do for you. Ask what you can do for your country." }
text
git clone https://github.com/huggingface/candle.git
text
git clone https://github.com/huggingface/candle.git
text
cargo clean
text
cargo clean
text
cargo run --example whisper --release --features symphonia -- --model distil-large-v3
text
cargo run --example whisper --release --features symphonia -- --model distil-large-v3
bash
pip install --upgrade pip
pip install --upgrade transformers datasets[audio] evaluate jiwer
bash
pip install --upgrade pip
pip install --upgrade transformers datasets[audio] evaluate jiwer

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Try Free API

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Deploy Now

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.