---
license: cc-by-nd-4.0
datasets:
- google/fleurs
- mozilla-foundation/common_voice_16_1
- joujiboi/japanese-anime-speech
language:
- ja
metrics:
- wer
library_name: transformers
pipeline_tag: automatic-speech-recognition
---
How to use:


audio_file ="path/to/audio_file"

model = "sin2piusc/whisper-medium-JP-5k"

pipe = pipeline("automatic-speech-recognition", "model")

pipe(audio_file, generate_kwargs={"language": "japanese", "task":"translate"})

--
or
--


client = InferenceClient(model, token="hf_token")

client.automatic_speech_recognition(audio_file).text


--
--
Make sure to set task and language.









--




--Original sentence:

集団内のすべての個体が特定の表現形質に関して同一である場合 それらは単形性と呼ばれます。

When all individuals in a population are identical with respect to a particular phenotypic trait, they are called monomorphic.

--sin2piusc/whisper-medium-5k:

集団内のすべての個体が特定の表現形質に関して同一である場合 それらは単形性と呼ばれます

When all individuals in a population are identical with respect to a particular phenotypic trait, they are called monomorphic.

--openai/whisper-medium:

集団内のすべての個体が特定の表現形式に関して同一である場合、それらは単形性と呼ばれます。

If all individuals in a population are identical with respect to a particular form of expression, they are called monomorphic.