Wav2vec2 Nepali Stt

🚀 語音轉錄模型

本模型可直接用於尼泊爾語語音轉錄，無需額外語言模型支持，操作簡單高效。

🚀 快速開始

該模型可以直接（無需語言模型）按以下方式使用：

import soundfile as sf
import torch
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
import argparse

def parse_transcription(wav_file):
    # load pretrained model
    processor = Wav2Vec2Processor.from_pretrained("addy88/wav2vec2-nepali-stt")
    model = Wav2Vec2ForCTC.from_pretrained("addy88/wav2vec2-nepali-stt")
    # load audio
    audio_input, sample_rate = sf.read(wav_file)
    # pad input values and return pt tensor
    input_values = processor(audio_input, sampling_rate=sample_rate, return_tensors="pt").input_values
    # INFERENCE
    # retrieve logits & take argmax
    logits = model(input_values).logits
    predicted_ids = torch.argmax(logits, dim=-1)
    # transcribe
    transcription = processor.decode(predicted_ids[0], skip_special_tokens=True)
    print(transcription)

💻 使用示例

基礎用法

import soundfile as sf
import torch
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
import argparse

def parse_transcription(wav_file):
    # load pretrained model
    processor = Wav2Vec2Processor.from_pretrained("addy88/wav2vec2-nepali-stt")
    model = Wav2Vec2ForCTC.from_pretrained("addy88/wav2vec2-nepali-stt")
    # load audio
    audio_input, sample_rate = sf.read(wav_file)
    # pad input values and return pt tensor
    input_values = processor(audio_input, sampling_rate=sample_rate, return_tensors="pt").input_values
    # INFERENCE
    # retrieve logits & take argmax
    logits = model(input_values).logits
    predicted_ids = torch.argmax(logits, dim=-1)
    # transcribe
    transcription = processor.decode(predicted_ids[0], skip_special_tokens=True)
    print(transcription)