japanese-wav2vec2-large-rs35kh

japanese-wav2vec2-large-rs35kh

This model is a wav2vec 2.0 Large fine-tuned on the large-scale Japanese ASR corpus ReazonSpeech v2.0.

Usage

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-large-rs35kh",
    torch_dtype=torch.bfloat16,
    attn_implementation="flash_attention_2",
).to("cuda")
processor = AutoProcessor.from_pretrained("reazon-research/japanese-wav2vec2-large-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)

Test Results

We report the Character Error Rate (CER) of our model and the other wav2vec2 families.

We also report the CER for long-form speech.

Citation

@misc{reazon-research-japanese-wav2vec2-large-rs35kh,
  title={japanese-wav2vec2-large-rs35kh},
  author={Sasaki, Yuta},
  url = {https://huggingface.co/reazon-research/japanese-wav2vec2-large-rs35kh},
  year = {2024}
}

License

Apaceh Licence 2.0