Training in progress, step 500

config.json

@@ -0,0 +1,255 @@
+{
+  "architectures": [
+    "ASRModel"
+  ],
+  "attn_implementation": "flash_attention_2",
+  "audio_config": {
+    "_name_or_path": "zai-org/GLM-ASR-Nano-2512",
+    "architectures": [
+      "GlmAsrForConditionalGeneration"
+    ],
+    "audio_config": {
+      "_name_or_path": "",
+      "add_cross_attention": false,
+      "architectures": null,
+      "attention_dropout": 0.0,
+      "bos_token_id": null,
+      "chunk_size_feed_forward": 0,
+      "cross_attention_hidden_size": null,
+      "decoder_start_token_id": null,
+      "dtype": null,
+      "eos_token_id": null,
+      "finetuning_task": null,
+      "head_dim": 64,
+      "hidden_act": "gelu",
+      "hidden_size": 1280,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "initializer_range": 0.02,
+      "intermediate_size": 5120,
+      "is_decoder": false,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "max_position_embeddings": 1500,
+      "model_type": "glmasr_encoder",
+      "num_attention_heads": 20,
+      "num_hidden_layers": 32,
+      "num_key_value_heads": 20,
+      "num_mel_bins": 128,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "pad_token_id": null,
+      "partial_rotary_factor": 0.5,
+      "prefix": null,
+      "problem_type": null,
+      "return_dict": true,
+      "rope_parameters": {
+        "partial_rotary_factor": 0.5,
+        "rope_theta": 10000.0,
+        "rope_type": "default"
+      },
+      "sep_token_id": null,
+      "task_specific_params": null,
+      "tie_word_embeddings": true,
+      "tokenizer_class": null
+    },
+    "audio_token_id": 59260,
+    "dtype": "bfloat16",
+    "hidden_size": 2048,
+    "model_type": "glmasr",
+    "num_mel_bins": 128,
+    "projector_hidden_act": "gelu",
+    "text_config": {
+      "_name_or_path": "",
+      "add_cross_attention": false,
+      "architectures": null,
+      "attention_bias": false,
+      "attention_dropout": 0.0,
+      "bos_token_id": 1,
+      "chunk_size_feed_forward": 0,
+      "cross_attention_hidden_size": null,
+      "decoder_start_token_id": null,
+      "dtype": null,
+      "eos_token_id": [
+        59246,
+        59253,
+        59255
+      ],
+      "finetuning_task": null,
+      "head_dim": 128,
+      "hidden_act": "silu",
+      "hidden_size": 2048,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "initializer_range": 0.02,
+      "intermediate_size": 6144,
+      "is_decoder": false,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "max_position_embeddings": 8192,
+      "mlp_bias": false,
+      "model_type": "llama",
+      "num_attention_heads": 16,
+      "num_hidden_layers": 28,
+      "num_key_value_heads": 4,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "pad_token_id": null,
+      "prefix": null,
+      "pretraining_tp": 1,
+      "problem_type": null,
+      "return_dict": true,
+      "rms_norm_eps": 1e-05,
+      "rope_parameters": {
+        "rope_theta": 10000.0,
+        "rope_type": "default"
+      },
+      "sep_token_id": null,
+      "task_specific_params": null,
+      "tie_word_embeddings": false,
+      "tokenizer_class": null,
+      "use_cache": true,
+      "vocab_size": 59264
+    },
+    "vocab_size": 59264
+  },
+  "audio_model_id": "zai-org/GLM-ASR-Nano-2512",
+  "audio_sample_rate": 16000,
+  "auto_map": {
+    "AutoConfig": "asr_config.ASRConfig",
+    "AutoModel": "asr_modeling.ASRModel",
+    "AutoModelForSpeechSeq2Seq": "asr_modeling.ASRModel",
+    "AutoProcessor": "asr_processing.ASRProcessor"
+  },
+  "custom_pipelines": {
+    "automatic-speech-recognition": {
+      "impl": "asr_pipeline.ASRPipeline",
+      "pt": [
+        "AutoModelForSpeechSeq2Seq"
+      ],
+      "tf": [],
+      "type": "audio"
+    }
+  },
+  "downsample_rate": 5,
+  "dtype": "bfloat16",
+  "encoder_conv_layers": [
+    [
+      1,
+      3,
+      1
+    ],
+    [
+      1,
+      3,
+      2
+    ]
+  ],
+  "encoder_dim": 1280,
+  "encoder_stride": 2,
+  "inference_warmup_tokens": 10,
+  "label_smoothing": 0.0,
+  "length_penalty": 1.0,
+  "llm_dim": 1024,
+  "max_new_tokens": 96,
+  "model_dtype": "bfloat16",
+  "model_type": "asr_model",
+  "no_repeat_ngram_size": 0,
+  "num_beams": 1,
+  "num_experts": 4,
+  "num_experts_per_tok": 2,
+  "pipeline_tag": "automatic-speech-recognition",
+  "projector_dropout": 0.0,
+  "projector_hidden_dim": null,
+  "projector_init_std": 0.02,
+  "projector_input_noise": 0.0,
+  "projector_num_layers": 2,
+  "projector_pool_stride": 4,
+  "projector_type": "mlp",
+  "qformer_hidden_size": null,
+  "qformer_intermediate_size": null,
+  "qformer_num_heads": 16,
+  "qformer_num_layers": 2,
+  "qformer_window_size": 15,
+  "repetition_penalty": 1.0,
+  "router_aux_loss_coef": 0.01,
+  "system_prompt": "/no_think /system_override",
+  "text_config": {
+    "_name_or_path": "Qwen/Qwen3-0.6B",
+    "architectures": [
+      "Qwen3ForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "dtype": "bfloat16",
+    "eos_token_id": 151645,
+    "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": 40960,
+    "max_window_layers": 28,
+    "model_type": "qwen3",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 8,
+    "pad_token_id": 151643,
+    "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": 151670
+  },
+  "text_model_id": "Qwen/Qwen3-0.6B",
+  "transformers_version": "5.0.0.dev0",
+  "use_cache": false,
+  "use_specaugment": true,
+  "user_prompt": "Please transcribe this English audio into text: <audio>",
+  "vocab_size": 151670
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "length_penalty": 1.0,
+  "max_new_tokens": 96,
+  "no_repeat_ngram_size": 0,
+  "num_beams": 1,
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.0,
+  "transformers_version": "5.0.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34ef36beee7b81b43b3a975fb4d9737a2e5d96e04e2c93cbd2aa9fc5c11a8e8a
+size 12583152

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8ee6c25214c15acbc5f2381a05f268e4d13b92ac59a9e9dee0a436f2dc53165
+size 5265