Upload folder using huggingface_hub

config.json

@@ -0,0 +1,314 @@
+{
+  "return_dict": true,
+  "output_hidden_states": false,
+  "torchscript": false,
+  "dtype": null,
+  "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": [
+    "Qwen3TTSForConditionalGeneration"
+  ],
+  "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": "Qwen/Qwen3-TTS-12Hz-1.7B-Base",
+  "transformers_version": "4.57.3",
+  "assistant_token_id": 77091,
+  "model_type": "qwen3_tts",
+  "tf_legacy_loss": false,
+  "use_bfloat16": false,
+  "talker_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": "",
+    "head_dim": 128,
+    "model_type": "qwen3_tts_talker",
+    "position_id_per_seconds": 13,
+    "text_vocab_size": 151936,
+    "tf_legacy_loss": false,
+    "use_bfloat16": false,
+    "vocab_size": 3072,
+    "max_position_embeddings": 32768,
+    "hidden_size": 2048,
+    "intermediate_size": 6144,
+    "num_hidden_layers": 28,
+    "num_attention_heads": 16,
+    "use_sliding_window": false,
+    "sliding_window": null,
+    "num_key_value_heads": 8,
+    "hidden_act": "silu",
+    "initializer_range": 0.02,
+    "rms_norm_eps": 1e-06,
+    "use_cache": true,
+    "rope_theta": 1000000,
+    "rope_scaling": {
+      "interleaved": true,
+      "mrope_section": [
+        24,
+        20,
+        20
+      ],
+      "rope_type": "default",
+      "type": "default"
+    },
+    "attention_bias": false,
+    "attention_dropout": 0,
+    "code_predictor_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": "qwen3_tts_talker_code_predictor",
+      "tf_legacy_loss": false,
+      "use_bfloat16": false,
+      "vocab_size": 2048,
+      "max_position_embeddings": 65536,
+      "hidden_size": 1024,
+      "intermediate_size": 3072,
+      "num_hidden_layers": 5,
+      "num_attention_heads": 16,
+      "use_sliding_window": false,
+      "sliding_window": null,
+      "max_window_layers": 28,
+      "num_key_value_heads": 8,
+      "head_dim": 128,
+      "hidden_act": "silu",
+      "initializer_range": 0.02,
+      "rms_norm_eps": 1e-06,
+      "use_cache": true,
+      "rope_theta": 1000000,
+      "rope_scaling": null,
+      "attention_bias": false,
+      "attention_dropout": 0,
+      "layer_types": [
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention"
+      ],
+      "num_code_groups": 16,
+      "output_attentions": false
+    },
+    "num_code_groups": 16,
+    "text_hidden_size": 2048,
+    "codec_eos_token_id": 2150,
+    "codec_think_id": 2154,
+    "codec_language_id": {
+      "chinese": 2055,
+      "english": 2050,
+      "german": 2053,
+      "italian": 2070,
+      "portuguese": 2071,
+      "spanish": 2054,
+      "japanese": 2058,
+      "korean": 2064,
+      "french": 2061,
+      "russian": 2069
+    },
+    "codec_nothink_id": 2155,
+    "codec_think_bos_id": 2156,
+    "codec_think_eos_id": 2157,
+    "codec_pad_id": 2148,
+    "codec_bos_id": 2149,
+    "spk_id": {
+      "darija_speaker": 3000
+    },
+    "spk_is_dialect": {
+      "darija_speaker": false
+    },
+    "output_attentions": false
+  },
+  "speaker_encoder_config": {
+    "mel_dim": 128,
+    "enc_dim": 2048,
+    "enc_channels": [
+      512,
+      512,
+      512,
+      512,
+      1536
+    ],
+    "enc_kernel_sizes": [
+      5,
+      3,
+      3,
+      3,
+      1
+    ],
+    "enc_dilations": [
+      1,
+      2,
+      3,
+      4,
+      1
+    ],
+    "enc_attention_channels": 128,
+    "enc_res2net_scale": 8,
+    "enc_se_channels": 128,
+    "sample_rate": 24000,
+    "model_type": ""
+  },
+  "tokenizer_type": "qwen3_tts_tokenizer_12hz",
+  "tts_model_size": "1b7",
+  "tts_model_type": "custom_voice",
+  "im_start_token_id": 151644,
+  "im_end_token_id": 151645,
+  "tts_pad_token_id": 151671,
+  "tts_bos_token_id": 151672,
+  "tts_eos_token_id": 151673,
+  "output_attentions": false
+}

speaker_embedding.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:245d00ee4d8ffaecee74e9f39b9250ac7654abf95645f4c0312dc15a3b42c873
+size 9903

talker_lora/README.md

@@ -0,0 +1,206 @@
+---
+base_model: ''
+library_name: peft
+tags:
+- 'base_model:adapter:'
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

talker_lora/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen3TTSTalkerModel",
+    "parent_library": "qwen_tts.core.models.modeling_qwen3_tts"
+  },
+  "base_model_name_or_path": "",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "v_proj",
+    "q_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": null,
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

talker_lora/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fccaf434b4cb39e2290699de41e1de4db6c6bdf8ba7a817c2146b1c27a5eebb
+size 12873296

training_meta.json

@@ -0,0 +1,17 @@
+{
+  "base_model": "Qwen/Qwen3-TTS-12Hz-1.7B-Base",
+  "speaker_name": "darija_speaker",
+  "speaker_id": 3000,
+  "epoch": 9,
+  "lora": {
+    "r": 8,
+    "alpha": 16,
+    "dropout": 0.05,
+    "target_modules": [
+      "q_proj",
+      "k_proj",
+      "v_proj",
+      "o_proj"
+    ]
+  }
+}