Model reference · open weights
japanese-wav2vec2-rs35kh is an open-weight audio or speech model from reazon-research. japanese-wav2vec2-base-rs35kh (FP32) weighs 193 MB; the smallest configuration that runs it is RTX 3060 12 GB.
For self-hosting, compare this build's requirements below with the GPU you plan to rent.
Summary of the reazon-research/japanese-wav2vec2-base-rs35kh model card, 2026-10-01
What it is
| Released by | reazon-research |
|---|---|
| Released | 2024-08-08 |
| Parameters | 97M |
| VRAM | 193 MB for the weights |
What it runs on
| Card | One stream | Memory |
|---|---|---|
| RTX 3060 12 GB | fits | 11.6 GB |
| RTX 4060 Ti 16 GB | fits | 15.4 GB |
| RTX 3090 24 GB | fits | 23.4 GB |
| RTX 4090 24 GB | fits | 23.4 GB |
| RTX 5090 32 GB | fits | 31.0 GB |
| L40S 48 GB | fits | 44.0 GB |
| A100 80 GB | fits | 78.2 GB |
| H100 80 GB | fits | 78.1 GB |
| RTX PRO 6000 Blackwell 96 GB | fits | 93.8 GB |
| DGX Spark (GB10) 128 GB unified | fits | 107 GB |
| H200 141 GB | fits | 138 GB |
| B200 180 GB | fits | 176 GB |
From the model card
This model is a wav2vec 2.0 Base fine-tuned on the large-scale Japanese ASR corpus ReazonSpeech v2.0.
You can use this model through transformers library:
import librosa
import numpy as np
from transformers import AutoProcessor, Wav2Vec2ForCTC
model = Wav2Vec2ForCTC.from_pretrained(
"reazon-research/japanese-wav2vec2-base-rs35kh",
torch_dtype=torch.bfloat16,
attn_implementation="flash_attention_2",
).to("cuda")
processor = AutoProcessor.from_pretrained("reazon-research/japanese-wav2vec2-base-rs35kh")
audio, _ = librosa.load(audio_filepath, sr=16_000)
audio = np.pad(audio, pad_width=int(0.5 * 16_000)) # Recommend to pad audio before inference
input_values = processor(
audio,
return_tensors="pt",
sampling_rate=16_000
).input_values.to("cuda").to(torch.bfloat16)
with torch.inference_mode():
logits = model(input_values).logits.cpu()
predicted_ids = torch.argmax(logits, dim=-1)[0]
transcription = processor.decode(predicted_ids, skip_special_tokens=True)
We report the Character Error Rate (CER) of our model and the other wav2vec2 families.
| Model | #Prameters⬇ | AVERAGE⬇ | JSUT-BASIC5000⬇ | Common Voice⬇ | TEDxJP-10K⬇ |
|---|---|---|---|---|---|
| reazon-research/japanese-wav2vec2-base-rs35kh | 96.7M | 20.40% | 13.22% | 23.76% | 24.23% |
| Ivydata/wav2vec2-large-xlsr-53-japanese | 318M | 24.23% | 13.83% | 18.15% | 40.72% |
| jonatasgrosman/wav2vec2-large-xlsr-53-japanese | 317M | 31.82% | 4.25% | 40.58% | 50.63% |
| vumichien/wav2vec2-large-xlsr-japanese | 318M | 39.87% | 4.21% | 53.29% | 62.12% |
We also report the CER for long-form speech.
| Model | #Prameters⬇ | JSUT-BOOK⬇ |
|---|---|---|
| reazon-research/japanese-wav2vec2-base-rs35kh | 96.7M | 82.84% |
| Ivydata/wav2vec2-large-xlsr-53-japanese | 318M | 65.60% |
| jonatasgrosman/wav2vec2-large-xlsr-53-japanese | 317M | 46.20% |
| vumichien/wav2vec2-large-xlsr-japanese | 318M | 46.52% |
@misc{reazon-research-japanese-wav2vec2-base-rs35kh,
title={japanese-wav2vec2-base-rs35kh},
author={Sasaki, Yuta},
url = {https://huggingface.co/reazon-research/japanese-wav2vec2-base-rs35kh},
year = {2024}
}
Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.