YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

FireRedASR-AED Model for vLLM

This model has been converted for use with vLLM.

Architecture

  • Encoder: Conformer (16 layers)
  • Decoder: Transformer (16 layers)
  • Model dimension: 1280
  • Attention heads: 20
  • Vocabulary size: 7832
  • Precision: BFLOAT16

Tokenizer

✓ Tokenizer 已从 FireRedASR dict.txt 转换并包含在模型目录中。

Usage

This model is designed for automatic speech recognition tasks.

Special Token IDs

  • BOS (Start): 3
  • EOS (End): 4
  • PAD (Padding): 2
Downloads last month
1
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support