Downloads · 30 days
29
26% of all-time downloads
Grushashunyalabsai/qwen3-asr-rakuten-multilingual-18lang
qwen3-asr-rakuten-multilingual-18lang is a automatic speech recognition model from Grushashunyalabsai. Use it when you need speech turned into text.
Fine-tuned Qwen3-ASR model for multilingual automatic speech recognition, optimized for Rakuten customer service use cases.
Downloads · 30 days
29
26% of all-time downloads
All-time downloads
113
Public
Parameters
2B
4.1 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors4.1 GB · 100%
From the Hugging Face model README
Fine-tuned Qwen3-ASR model for multilingual automatic speech recognition, optimized for Rakuten customer service use cases.
English, Chinese, French, Portuguese, Korean, Vietnamese, Hindi, Thai, Indonesian, Tamil, Urdu, Nepali, Uzbek, Mongolian, Sinhala, Burmese, Japanese, Italian
pip install -U qwen-asr
import torch
from qwen_asr import Qwen3ASRModel
model_path = "Grushashunyalabsai/qwen3-asr-rakuten-multilingual-18lang"
device = "cuda:0" if torch.cuda.is_available() else "cpu"
dtype = torch.bfloat16 if device.startswith("cuda") else torch.float32
asr = Qwen3ASRModel.from_pretrained(
model_path,
dtype=dtype,
device_map=device,
max_inference_batch_size=16,
max_new_tokens=440,
)
# Single file (auto-detect language)
results = asr.transcribe(audio="audio.wav")
print(results[0].language) # e.g. "Japanese"
print(results[0].text) # transcribed text
# Force a specific language
results = asr.transcribe(audio="audio.wav", language="Japanese")
# From numpy array (16kHz mono)
import numpy as np
audio_array = np.zeros(16000, dtype=np.float32) # 1 sec
results = asr.transcribe(audio=(audio_array, 16000))
# Batch processing
results = asr.transcribe(
audio=["file1.wav", "file2.wav", "file3.wav"],
language=["Japanese", "English", "Hindi"],
)
for r in results:
print(f"{r.language}: {r.text}")
# Auto-detect language
python infer.py audio.wav
# Force language
python infer.py audio.wav --language Japanese
# Batch folder to JSONL
python infer.py ./audio_dir --out results.jsonl
The model accepts:
.wav, .flac, .mp3, .m4a, .ogg, .opus, .webm(np.ndarray, sample_rate) tuple@dataclass
class ASRTranscription:
language: str # e.g. "Japanese", "English", "Chinese,English"
text: str # Transcribed text
time_stamps: Optional[Any] # Word-level timestamps (if requested)
model.safetensors — Model weights (bf16)config.json — Model configurationtokenizer_config.json — Tokenizer configurationvocab.json — Vocabularymerges.txt — BPE mergesinfer.py — CLI inference scriptpreprocessor_config.json — Audio preprocessor config