64 lines
2.4 KiB
Markdown
64 lines
2.4 KiB
Markdown
---
|
|
license: apache-2.0
|
|
datasets:
|
|
- common_voice
|
|
language:
|
|
- ja
|
|
tags:
|
|
- audio
|
|
---
|
|
|
|
# Fine-tuned Japanese Whisper model for speech recognition using whisper-small
|
|
Fine-tuned [openai/whisper-small](https://huggingface.co/openai/whisper-small) on Japanese using [Common Voice](https://commonvoice.mozilla.org/ja/datasets), [JVS](https://sites.google.com/site/shinnosuketakamichi/research-topics/jvs_corpus) and [JSUT](https://sites.google.com/site/shinnosuketakamichi/publication/jsut).
|
|
When using this model, make sure that your speech input is sampled at 16kHz.
|
|
|
|
## Usage
|
|
The model can be used directly as follows.
|
|
```python
|
|
from transformers import WhisperForConditionalGeneration, WhisperProcessor
|
|
from datasets import load_dataset
|
|
import librosa
|
|
import torch
|
|
|
|
LANG_ID = "ja"
|
|
MODEL_ID = "Ivydata/whisper-small-japanese"
|
|
SAMPLES = 10
|
|
|
|
test_dataset = load_dataset("common_voice", LANG_ID, split=f"test[:{SAMPLES}]")
|
|
processor = WhisperProcessor.from_pretrained(MODEL_ID)
|
|
model = WhisperForConditionalGeneration.from_pretrained(MODEL_ID)
|
|
model.config.forced_decoder_ids = processor.get_decoder_prompt_ids(
|
|
language="ja", task="transcribe"
|
|
)
|
|
model.config.suppress_tokens = []
|
|
|
|
# Preprocessing the datasets.
|
|
# We need to read the audio files as arrays
|
|
def speech_file_to_array_fn(batch):
|
|
speech_array, sampling_rate = librosa.load(batch["path"], sr=16_000)
|
|
batch["speech"] = speech_array
|
|
batch["sentence"] = batch["sentence"].upper()
|
|
batch["sampling_rate"] = sampling_rate
|
|
return batch
|
|
|
|
test_dataset = test_dataset.map(speech_file_to_array_fn)
|
|
sample = test_dataset[0]
|
|
input_features = processor(sample["speech"], sampling_rate=sample["sampling_rate"], return_tensors="pt").input_features
|
|
predicted_ids = model.generate(input_features)
|
|
|
|
transcription = processor.batch_decode(predicted_ids, skip_special_tokens=False)
|
|
# ['<|startoftranscript|><|ja|><|transcribe|><|notimestamps|>木村さんに電話を貸してもらいました。<|endoftext|>']
|
|
|
|
transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)
|
|
# ['木村さんに電話を貸してもらいました。']
|
|
|
|
```
|
|
|
|
## Test Result
|
|
|
|
In the table below I report the Character Error Rate (CER) of the model tested on [TEDxJP-10K](https://github.com/laboroai/TEDxJP-10K) dataset.
|
|
| Model | CER |
|
|
| ------------- | ------------- |
|
|
| Ivydata/whisper-small-japanese | **23.10%** |
|
|
| Ivydata/wav2vec2-large-xlsr-53-japanese | **27.87%** |
|
|
| jonatasgrosman/wav2vec2-large-xlsr-53-japanese | 34.18% | |