hackit/mate-local-models
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

voice: add Marvis TTS 250m v0.2 (MLX 8bit/4bit) + Kyutai Mimi codec (CC-BY-4.0)

Browse source
This commit is contained in:
hackit 2026-07-14 21:57:21 +00:00
parent 4cea3f7301
commit 5247c06789
38 changed files with 1657 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

307
voice/mlx/Marvis-AI/marvis-tts-250m-v0.2-MLX-8bit/config.json Executable file
View file

@ -0,0 +1,307 @@
{
"add_cross_attention": false,
"architectures": [
"CsmForConditionalGeneration"
],
"attention_bias": false,
"attention_dropout": 0.0,
"audio_eos_token_id": 128003,
"audio_num_codebooks": 32,
"audio_token_id": 128002,
"audio_vocab_size": 2051,
"backbone_flavor": "llama-250M",
"bad_words_ids": null,
"begin_suppress_tokens": null,
"bos_token_id": 128000,
"chunk_size_feed_forward": 0,
"codebook_eos_token_id": 0,
"codebook_pad_token_id": 2050,
"codec_config": {
"sampling_rate": 24000,
"audio_channels": 1,
"hidden_size": 512,
"num_filters": 64,
"num_residual_layers": 1,
"upsampling_ratios": [
8,
6,
5,
4
],
"kernel_size": 7,
"last_kernel_size": 3,
"residual_kernel_size": 3,
"dilation_growth_rate": 2,
"use_causal_conv": true,
"pad_mode": "constant",
"compress": 2,
"trim_right_ratio": 1.0,
"codebook_size": 2048,
"codebook_dim": 256,
"num_quantizers": 32,
"use_conv_shortcut": false,
"vector_quantization_hidden_dimension": 256,
"upsample_groups": 512,
"num_hidden_layers": 8,
"intermediate_size": 2048,
"num_attention_heads": 8,
"num_key_value_heads": 8,
"hidden_act": "gelu",
"max_position_embeddings": 8000,
"initializer_range": 0.02,
"norm_eps": 1e-05,
"use_cache": false,
"use_streaming": false,
"rope_theta": 10000.0,
"sliding_window": 250,
"attention_dropout": 0.0,
"head_dim": 64,
"layer_scale_initial_scale": 0.01,
"attention_bias": false,
"_frame_rate": 12.5,
"num_semantic_quantizers": 1,
"return_dict": true,
"output_hidden_states": false,
"torchscript": false,
"dtype": "float32",
"pruned_heads": {},
"tie_word_embeddings": true,
"chunk_size_feed_forward": 0,
"is_encoder_decoder": false,
"is_decoder": false,
"cross_attention_hidden_size": null,
"add_cross_attention": false,
"tie_encoder_decoder": false,
"architectures": [
"MimiModel"
],
"finetuning_task": null,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"task_specific_params": null,
"problem_type": null,
"tokenizer_class": null,
"prefix": null,
"bos_token_id": null,
"pad_token_id": null,
"eos_token_id": null,
"sep_token_id": null,
"decoder_start_token_id": null,
"max_length": 20,
"min_length": 0,
"do_sample": false,
"early_stopping": false,
"num_beams": 1,
"temperature": 1.0,
"top_k": 50,
"top_p": 1.0,
"typical_p": 1.0,
"repetition_penalty": 1.0,
"length_penalty": 1.0,
"no_repeat_ngram_size": 0,
"encoder_no_repeat_ngram_size": 0,
"bad_words_ids": null,
"num_return_sequences": 1,
"output_scores": false,
"return_dict_in_generate": false,
"forced_bos_token_id": null,
"forced_eos_token_id": null,
"remove_invalid_values": false,
"exponential_decay_length_penalty": null,
"suppress_tokens": null,
"begin_suppress_tokens": null,
"num_beam_groups": 1,
"diversity_penalty": 0.0,
"_name_or_path": "kyutai/mimi",
"normalize": false,
"tf_legacy_loss": false,
"use_bfloat16": false,
"model_type": "mimi",
"output_attentions": false
},
"cross_attention_hidden_size": null,
"decoder_flavor": "llama-60M",
"decoder_start_token_id": null,
"depth_decoder_config": {
"return_dict": true,
"output_hidden_states": false,
"torchscript": false,
"dtype": null,
"pruned_heads": {},
"tie_word_embeddings": false,
"chunk_size_feed_forward": 0,
"is_encoder_decoder": false,
"is_decoder": false,
"cross_attention_hidden_size": null,
"add_cross_attention": false,
"tie_encoder_decoder": false,
"architectures": null,
"finetuning_task": null,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"task_specific_params": null,
"problem_type": null,
"tokenizer_class": null,
"prefix": null,
"bos_token_id": null,
"pad_token_id": null,
"eos_token_id": null,
"sep_token_id": null,
"decoder_start_token_id": null,
"max_length": 20,
"min_length": 0,
"do_sample": false,
"early_stopping": false,
"num_beams": 1,
"temperature": 1.0,
"top_k": 50,
"top_p": 1.0,
"typical_p": 1.0,
"repetition_penalty": 1.0,
"length_penalty": 1.0,
"no_repeat_ngram_size": 0,
"encoder_no_repeat_ngram_size": 0,
"bad_words_ids": null,
"num_return_sequences": 1,
"output_scores": false,
"return_dict_in_generate": false,
"forced_bos_token_id": null,
"forced_eos_token_id": null,
"remove_invalid_values": false,
"exponential_decay_length_penalty": null,
"suppress_tokens": null,
"begin_suppress_tokens": null,
"num_beam_groups": 1,
"diversity_penalty": 0.0,
"_name_or_path": "",
"model_type": "csm_depth_decoder_model",
"tf_legacy_loss": false,
"use_bfloat16": false,
"num_codebooks": 32,
"vocab_size": 2051,
"backbone_hidden_size": 1536,
"max_position_embeddings": 33,
"hidden_size": 1024,
"intermediate_size": 4096,
"num_hidden_layers": 4,
"num_attention_heads": 8,
"num_key_value_heads": 2,
"hidden_act": "silu",
"initializer_range": 0.02,
"rms_norm_eps": 1e-05,
"use_cache": true,
"rope_theta": 500000,
"rope_scaling": {
"factor": 32.0,
"high_freq_factor": 0.0078125,
"low_freq_factor": 0.001953125,
"original_max_position_embeddings": 16,
"rope_type": "llama3"
},
"attention_bias": false,
"attention_dropout": 0.0,
"mlp_bias": false,
"head_dim": 128,
"output_attentions": false
},
"diversity_penalty": 0.0,
"do_sample": false,
"dtype": null,
"early_stopping": false,
"encoder_no_repeat_ngram_size": 0,
"eos_token_id": null,
"exponential_decay_length_penalty": null,
"finetuning_task": null,
"forced_bos_token_id": null,
"forced_eos_token_id": null,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 1536,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"initializer_range": 0.02,
"intermediate_size": 8192,
"is_decoder": false,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"length_penalty": 1.0,
"max_length": 20,
"max_position_embeddings": 2048,
"min_length": 0,
"mlp_bias": false,
"model_type": "csm",
"no_repeat_ngram_size": 0,
"num_attention_heads": 12,
"num_beam_groups": 1,
"num_beams": 1,
"num_codebooks": 32,
"num_hidden_layers": 6,
"num_key_value_heads": 3,
"num_return_sequences": 1,
"output_attentions": false,
"output_hidden_states": false,
"output_scores": false,
"pad_token_id": 128002,
"prefix": null,
"problem_type": null,
"pruned_heads": {},
"quantization": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"quantization_config": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"remove_invalid_values": false,
"repetition_penalty": 1.0,
"return_dict": true,
"return_dict_in_generate": false,
"rms_norm_eps": 1e-05,
"rope_scaling": {
"factor": 32.0,
"high_freq_factor": 0.5,
"low_freq_factor": 0.125,
"original_max_position_embeddings": 1024,
"rope_type": "llama3"
},
"rope_theta": 500000,
"sep_token_id": null,
"suppress_tokens": null,
"task_specific_params": null,
"temperature": 1.0,
"text_tokenizer": "Marvis-AI/marvis-tts-250m-v0.2",
"text_vocab_size": 49152,
"tf_legacy_loss": false,
"tie_codebooks_embeddings": true,
"tie_encoder_decoder": false,
"tie_word_embeddings": false,
"tokenizer_class": null,
"top_k": 50,
"top_p": 1.0,
"torchscript": false,
"transformers_version": "4.57.1",
"typical_p": 1.0,
"use_bfloat16": false,
"use_cache": true,
"vocab_size": 2051
}