Added Model

D_800000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea05db6071d319a7d586e437ca10baf1367d8a1e2136c8bfae19b515c4e8b5af
+size 561099642

G_800000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7acf75d12d84635f2a96b6a5aedaf6602c9b4415e8b5b36e9ce711008448878f
+size 438217614

README.md

@@ -1,3 +1,48 @@
 ---
-license: apache-2.0
+language: sw
+license: cc-by-sa-4.0
+tags:
+  - audio
+  - text-to-speech
+inference: false
+datasets:
+  - bookbot/OpenBible_Swahili
 ---
+
+# VITS Base sw-KE-OpenBible
+
+VITS Base sw-KE-OpenBible is an end-to-end text-to-speech model based on the [VITS](https://arxiv.org/abs/2106.06103) architecture. This model was trained from scratch on a real audio dataset. The list of real speakers include:
+
+- sw-KE-OpenBible
+
+The model's [vocabulary](https://huggingface.co/bookbot/vits-base-sw-KE-OpenBible/blob/main/symbols.py) contains the different IPA phonemes found in [gruut](https://github.com/rhasspy/gruut).
+
+This model was trained using [VITS](https://github.com/jaywalnut310/vits) framework. All training was done on a Scaleway L40S VM with a NVIDIA L40S GPU. All necessary scripts used for training could be found in the [Files and versions](https://huggingface.co/bookbot/vits-base-sw-KE-OpenBible/tree/main) tab, as well as the [Training metrics](https://huggingface.co/bookbot/vits-base-sw-KE-OpenBible/tensorboard) logged via Tensorboard.
+
+## Model
+
+| Model                     | SR (Hz) | Mel range (Hz) | FFT / Hop / Win   | #epochs |
+| ------------------------- | ------- | -------------- | ----------------- | ------- |
+| VITS Base sw-KE-OpenBible | 44.1K   | 0-null         | 2048 / 512 / 2048 | 12000   |
+
+## Training procedure
+
+### Prepare Data
+
+```sh
+python preprocess.py \
+    --text_index 1 \
+    --filelists filelists/sw-KE-OpenBible_text_train_filelist.txt filelists/sw-KE-OpenBible_text_val_filelist.txt \
+    --text_cleaners swahili_cleaners
+```
+
+### Train
+
+```sh
+python train.py -c configs/sw_ke_openbible_base.json -m sw_ke_openbible_base
+```
+
+## Frameworks
+
+- PyTorch 2.2.2
+- [VITS](https://github.com/bookbot-hive/vits)

config.json

@@ -0,0 +1,89 @@
+{
+  "train": {
+    "log_interval": 200,
+    "eval_interval": 100000,
+    "seed": 1234,
+    "epochs": 12000,
+    "learning_rate": 2e-4,
+    "betas": [
+      0.8,
+      0.99
+    ],
+    "eps": 1e-9,
+    "batch_size": 64,
+    "fp16_run": true,
+    "lr_decay": 0.999875,
+    "segment_size": 8192,
+    "init_lr_ratio": 1,
+    "warmup_epochs": 0,
+    "c_mel": 45,
+    "c_kl": 1.0
+  },
+  "data": {
+    "training_files": "filelists/sw-KE-OpenBible_text_train_filelist.txt.cleaned",
+    "validation_files": "filelists/sw-KE-OpenBible_text_val_filelist.txt.cleaned",
+    "text_cleaners": [
+      "swahili_cleaners"
+    ],
+    "max_wav_value": 1.0,
+    "sampling_rate": 44100,
+    "filter_length": 2048,
+    "hop_length": 512,
+    "win_length": 2048,
+    "n_mel_channels": 80,
+    "mel_fmin": 0.0,
+    "mel_fmax": null,
+    "add_blank": true,
+    "n_speakers": 0,
+    "cleaned_text": true
+  },
+  "model": {
+    "inter_channels": 192,
+    "hidden_channels": 192,
+    "filter_channels": 768,
+    "n_heads": 2,
+    "n_layers": 6,
+    "kernel_size": 3,
+    "p_dropout": 0.1,
+    "resblock": "1",
+    "resblock_kernel_sizes": [
+      3,
+      7,
+      11
+    ],
+    "resblock_dilation_sizes": [
+      [
+        1,
+        3,
+        5
+      ],
+      [
+        1,
+        3,
+        5
+      ],
+      [
+        1,
+        3,
+        5
+      ]
+    ],
+    "upsample_rates": [
+      8,
+      8,
+      2,
+      2,
+      2
+    ],
+    "upsample_initial_channel": 512,
+    "upsample_kernel_sizes": [
+      16,
+      16,
+      4,
+      4,
+      4
+    ],
+    "n_layers_q": 3,
+    "use_spectral_norm": false
+  }
+}

eval/events.out.tfevents.1713522751.bookbot-l40s.75863.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb67df477e4d2e8492f9ab32f08446179e2c97d4e30ce03710c0d1a0adf99bdf
+size 7399613

events.out.tfevents.1713522751.bookbot-l40s.75863.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f58a06f01d3f10c0aac2d1c93cda6171e16fceafd091aeda70d2ed3c0f0454fa
+size 516111967

symbols.py

@@ -0,0 +1,51 @@
+""" from https://github.com/keithito/tacotron """
+
+"""
+Defines the set of symbols used in text input to the model.
+"""
+_pad = "_"
+_punctuation = ";:,.!? "
+_letters_ipa = [
+    "f",
+    "h",
+    "i",
+    "j",
+    "k",
+    "l",
+    "m",
+    "n",
+    "p",
+    "s",
+    "t",
+    "t͡ʃ",
+    "u",
+    "v",
+    "w",
+    "x",
+    "z",
+    "ð",
+    "ɑ",
+    "ɓ",
+    "ɔ",
+    "ɗ",
+    "ɛ",
+    "ɠ",
+    "ɣ",
+    "ɾ",
+    "ʃ",
+    "ʄ",
+    "θ",
+    "ᵐɓ",
+    "ᵑg",
+    "ᶬv",
+    "ⁿz",
+    "ⁿɗ",
+    "ⁿɗ͡ʒ",
+]
+
+
+# Export all symbols:
+symbols = [_pad] + list(_punctuation) + _letters_ipa
+
+# Special symbol ids
+SPACE_ID = symbols.index(" ")