Qwen3-ASR-0.6B / config.json
bezzam's picture
bezzam HF Staff
Upload Qwen3ASRForConditionalGeneration
3057211 verified
{
"architectures": [
"Qwen3ASRForConditionalGeneration"
],
"audio_config": {
"activation_dropout": 0,
"activation_function": "gelu",
"attention_dropout": 0,
"conv_chunksize": 500,
"d_model": 896,
"downsample_hidden_size": 480,
"dropout": 0,
"encoder_attention_heads": 14,
"encoder_ffn_dim": 3584,
"encoder_layers": 18,
"initializer_range": 0.02,
"max_source_positions": 1500,
"model_type": "qwen3_omni_moe_audio_encoder",
"n_window": 50,
"n_window_infer": 800,
"num_mel_bins": 128,
"output_dim": 1024,
"scale_embedding": false
},
"audio_token_id": 151676,
"dtype": "bfloat16",
"eos_token_id": [
151643,
151645
],
"initializer_range": 0.02,
"model_type": "qwen3_asr",
"pad_token_id": 151645,
"text_config": {
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": null,
"eos_token_id": null,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 1024,
"initializer_range": 0.02,
"intermediate_size": 3072,
"layer_types": [
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention"
],
"max_position_embeddings": 65536,
"max_window_layers": 28,
"model_type": "qwen3",
"num_attention_heads": 16,
"num_hidden_layers": 28,
"num_key_value_heads": 8,
"pad_token_id": null,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"rope_theta": 1000000,
"rope_type": "default"
},
"sliding_window": null,
"tie_word_embeddings": true,
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151936
},
"transformers_version": "5.6.0.dev0"
}