Tts Hubert Cluster Bart Base

🚀 voidful/tts_hubert_cluster_bart_base

A model for automatic speech recognition, leveraging the Hubert architecture and suitable for audio - related tasks.

🚀 Quick Start

✨ Features

• Datasets: Utilizes the Librispeech dataset.
• Tags: Related to audio, automatic speech recognition, speech, ASR, and Hubert.
• License: Licensed under the Apache - 2.0 license.
• Metrics: Evaluated using WER (Word Error Rate) and CER (Character Error Rate).

📦 Installation

No specific installation steps are provided in the original document.

💻 Usage Examples

Basic Usage

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
tokenizer = AutoTokenizer.from_pretrained("voidful/tts_hubert_cluster_bart_base")
model = AutoModelForSeq2SeqLM.from_pretrained("voidful/tts_hubert_cluster_bart_base")

Advanced Usage

# Generate output
gen_output = model.generate(input_ids=tokenizer("going along slushy country roads and speaking to damp audience in drifty school rooms day after day for a fortnight he'll have to put in an appearance at some place of worship on sunday morning and he can come to ask immediately afterwards",return_tensors='pt').input_ids, max_length=1024)
print(tokenizer.decode(gen_output[0], skip_special_tokens=True))

📚 Documentation

Result

The output result is as follows: :vtok402::vtok329::vtok329::vtok75::vtok75::vtok75::vtok44::vtok150::vtok150::vtok222::vtok280::vtok280::vtok138::vtok409::vtok409::vtok409::vtok46::vtok441:

📄 License

This project is licensed under the Apache - 2.0 license.