Upload Okyeame TTS fine-tuned XTTS v2 model

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+reference.wav filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,43 @@
+---
+language: en
+tags:
+  - tts
+  - xtts
+  - coqui
+  - ghanaian-english
+  - voice-cloning
+license: apache-2.0
+library_name: coqui-tts
+---
+
+# Okyeame TTS — Ghanaian English XTTS v2 Fine-tune
+
+Fine-tuned [XTTS v2](https://huggingface.co/coqui/XTTS-v2) model for Ghanaian-accented English speech synthesis.
+
+## Usage
+
+```python
+from TTS.api import TTS
+
+tts = TTS()
+tts.load_tts_model_by_path(
+    model_path="model.pth",
+    config_path="config.json"
+)
+tts.tts_to_file(
+    text="Good morning, how are you doing today?",
+    speaker_wav="reference.wav",
+    language="en",
+    file_path="output.wav"
+)
+```
+
+## Training Data
+
+Trained on the [Ghana English ASR 2700hrs](https://huggingface.co/datasets/ghananlpcommunity/ghana-english-asr-2700hrs) dataset.
+
+## Model Details
+
+- **Base model**: XTTS v2 (Coqui)
+- **Fine-tuning**: GPT decoder layers
+- **Sample rate**: 22050 Hz (internal), 24000 Hz (output)

config.json

@@ -0,0 +1,191 @@
+{
+    "output_path": "/kaggle/working/run/training",
+    "logger_uri": null,
+    "run_name": "okyeame_xtts_ft",
+    "project_name": "okyeame-tts",
+    "run_description": "Okyeame TTS - Ghanaian English XTTS v2 fine-tuning",
+    "print_step": 50,
+    "plot_step": 100,
+    "model_param_stats": false,
+    "wandb_entity": null,
+    "dashboard_logger": "tensorboard",
+    "save_on_interrupt": true,
+    "log_model_step": 100,
+    "save_step": 9000,
+    "save_n_checkpoints": 1,
+    "save_checkpoints": false,
+    "save_all_best": false,
+    "save_best_after": 0,
+    "target_loss": null,
+    "print_eval": false,
+    "test_delay_epochs": 0,
+    "run_eval": true,
+    "run_eval_steps": null,
+    "distributed_backend": "nccl",
+    "distributed_url": "tcp://localhost:54321",
+    "mixed_precision": false,
+    "precision": "fp16",
+    "epochs": 1,
+    "batch_size": 3,
+    "eval_batch_size": 3,
+    "grad_clip": null,
+    "scheduler_after_epoch": true,
+    "lr": 5e-06,
+    "optimizer": "AdamW",
+    "optimizer_params": {
+        "betas": [
+            0.9,
+            0.96
+        ],
+        "eps": 1e-08,
+        "weight_decay": 0.01
+    },
+    "lr_scheduler": "MultiStepLR",
+    "lr_scheduler_params": {
+        "milestones": [
+            900000,
+            2700000,
+            5400000
+        ],
+        "gamma": 0.5,
+        "last_epoch": -1
+    },
+    "use_grad_scaler": false,
+    "allow_tf32": false,
+    "cudnn_enable": true,
+    "cudnn_deterministic": false,
+    "cudnn_benchmark": false,
+    "training_seed": 1,
+    "model": "xtts",
+    "num_loader_workers": 4,
+    "num_eval_loader_workers": 0,
+    "use_noise_augment": false,
+    "audio": {
+        "sample_rate": 22050,
+        "output_sample_rate": 24000,
+        "dvae_sample_rate": 22050
+    },
+    "model_args": {
+        "gpt_batch_size": 1,
+        "enable_redaction": false,
+        "kv_cache": true,
+        "gpt_checkpoint": "",
+        "clvp_checkpoint": null,
+        "decoder_checkpoint": null,
+        "num_chars": 67,
+        "tokenizer_file": "/kaggle/working/run/training/XTTS_v2_original/vocab.json",
+        "gpt_max_audio_tokens": 605,
+        "gpt_max_text_tokens": 402,
+        "gpt_max_prompt_tokens": 70,
+        "gpt_layers": 30,
+        "gpt_n_model_channels": 1024,
+        "gpt_n_heads": 16,
+        "gpt_number_text_tokens": 6681,
+        "gpt_start_text_token": 261,
+        "gpt_stop_text_token": 0,
+        "gpt_num_audio_tokens": 1026,
+        "gpt_start_audio_token": 1024,
+        "gpt_stop_audio_token": 1025,
+        "gpt_code_stride_len": 1024,
+        "gpt_use_masking_gt_prompt_approach": true,
+        "gpt_use_perceiver_resampler": true,
+        "input_sample_rate": 22050,
+        "output_sample_rate": 24000,
+        "output_hop_length": 256,
+        "decoder_input_dim": 1024,
+        "d_vector_dim": 512,
+        "cond_d_vector_in_each_upsampling_layer": true,
+        "duration_const": 102400,
+        "min_conditioning_length": 22050,
+        "max_conditioning_length": 132300,
+        "gpt_loss_text_ce_weight": 0.01,
+        "gpt_loss_mel_ce_weight": 1.0,
+        "debug_loading_failures": false,
+        "max_wav_length": 255995,
+        "max_text_length": 200,
+        "mel_norm_file": "/kaggle/working/run/training/XTTS_v2_original/mel_stats.pth",
+        "dvae_checkpoint": "/kaggle/working/run/training/XTTS_v2_original/dvae.pth",
+        "xtts_checkpoint": "/kaggle/working/run/training/XTTS_v2_original/model.pth",
+        "vocoder": ""
+    },
+    "_supports_cloning": true,
+    "languages": [
+        "en",
+        "es",
+        "fr",
+        "de",
+        "it",
+        "pt",
+        "pl",
+        "tr",
+        "ru",
+        "nl",
+        "cs",
+        "ar",
+        "zh-cn",
+        "hu",
+        "ko",
+        "ja",
+        "hi"
+    ],
+    "speakers": [],
+    "use_phonemes": false,
+    "phonemizer": null,
+    "phoneme_language": null,
+    "compute_input_seq_cache": false,
+    "text_cleaner": null,
+    "enable_eos_bos_chars": false,
+    "test_sentences_file": "",
+    "phoneme_cache_path": null,
+    "characters": null,
+    "add_blank": false,
+    "batch_group_size": 48,
+    "loss_masking": null,
+    "min_audio_len": 1,
+    "max_audio_len": Infinity,
+    "min_text_len": 1,
+    "max_text_len": Infinity,
+    "compute_f0": false,
+    "compute_energy": false,
+    "compute_linear_spec": false,
+    "precompute_num_workers": 0,
+    "start_by_longest": false,
+    "shuffle": false,
+    "drop_last": false,
+    "datasets": [
+        {
+            "formatter": "coqui",
+            "dataset_name": "okyeame_dataset",
+            "path": "/kaggle/working",
+            "meta_file_train": "/kaggle/working/metadata_train.csv",
+            "ignored_speakers": null,
+            "language": "en",
+            "phonemizer": "",
+            "meta_file_val": "/kaggle/working/metadata_eval.csv",
+            "meta_file_attn_mask": ""
+        }
+    ],
+    "test_sentences": [],
+    "eval_split_max_size": 256,
+    "eval_split_size": 0.01,
+    "use_speaker_weighted_sampler": false,
+    "speaker_weighted_sampler_alpha": 1.0,
+    "use_language_weighted_sampler": false,
+    "language_weighted_sampler_alpha": 1.0,
+    "use_length_weighted_sampler": false,
+    "length_weighted_sampler_alpha": 1.0,
+    "temperature": 0.85,
+    "length_penalty": 1.0,
+    "repetition_penalty": 2.0,
+    "top_k": 50,
+    "top_p": 0.85,
+    "num_gpt_outputs": 1,
+    "gpt_cond_len": 12,
+    "gpt_cond_chunk_len": 4,
+    "max_ref_len": 10,
+    "sound_norm_refs": false,
+    "optimizer_wd_only_on_weights": true,
+    "weighted_loss_attrs": null,
+    "weighted_loss_multipliers": null,
+    "github_branch": "inside_docker"
+}

dvae.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b29bc227d410d4991e0a8c09b858f77415013eeb9fba9650258e96095557d97a
+size 210514388

mel_stats.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f69422a8a8f344c4fca2f0c6b8d41d2151d6615b7321e48e6bb15ae949b119c
+size 1067

model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c16510c3b265f6bba156f4cd671cd82fe968de0d1a8da1729ee76610cf353421
+size 5607934838

reference.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b56b4690bacfba49c6f43f2c82a45763944b535cd69ed8ef2bf624d87ab08968
+size 185522