Downloads · 30 days
21
8% of all-time downloads
mms-tts-pko-east
speedykom-group/mms-tts-pko-east
mms-tts-pko-east is a text-to-speech model from speedykom-group. Use it when you need text read aloud. The card lists the license as cc-by-nc-4.0.
- HuggingFace ID: facebook/mms-tts-kpz (facebook/mms-tts-kpz) - Architecture: VITS — Variational Inference with adversarial learning for end-to-end TTS - HuggingFace ID: speedykom-group/pokoot-east-speech-dataset - Sp…
All-time downloads
259
Public
Parameters
36.3M
145 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors145 MB · 100%
At a glance
- Task
- Text-to-Speech
- License
- cc-by-nc-4.0
- Model type
- vits
- Access
- Public
- Created
- Apr 30, 2026
- Updated
- May 4, 2026
- SHA
- d3ed08c5
Base models
Model card
From the Hugging Face model README
MODEL CARD — Pokoot East TTS
Base Model
- HuggingFace ID:
facebook/mms-tts-kpz(facebook/mms-tts-kpz) - Architecture: VITS — Variational Inference with adversarial learning for end-to-end TTS
Dataset
- HuggingFace ID:
speedykom-group/pokoot-east-speech-dataset - Splits used: train / validation / test
- Size: see dataset card on HuggingFace Hub for exact utterance counts and total hours
- License of training data: see dataset card on HuggingFace Hub — verify before redistribution
Fine-tuning Details
- Trainable layers: text_encoder
- Optimizer: AdamW (lr=1e-05, betas=(0.8, 0.99), weight_decay=0.01)
- Scheduler: CosineAnnealingLR
- Batch size: 4 samples × 4 accumulation steps = effective batch 16
- Max epochs: 50 (early stopping on validation mel loss, patience=5)
- Best checkpoint: selected by minimum validation mel-spectrogram loss (L1)
Evaluation (Test Set)
Mel-spectrogram loss (L1) and MCD (Mel Cepstral Distortion, dB — lower is better)
Deliverable Files
| File | Description |
|---|---|
config.json | Model architecture config |
model.safetensors | Fine-tuned weights (preferred over .bin) |
tokenizer_config.json | Tokenizer settings |
vocab.json | Vocabulary mapping |
special_tokens_map.json | Special token definitions |
samples/ | 5 synthesised WAVs listened to and approved |
Sample Audio
Five synthesised WAVs are included in the samples/ folder.
Each has been listened to and approved before delivery.
| Pokoot East | English | Audio |
|---|---|---|
| Kwen koŋ kɨ mwaŋi. Terer kɨ mwoi. | Heavy rain is coming. Move to higher ground. | sample_01.wav |
| Wɨrwɨr koŋ ŋʼitechi. Lak kɨ awi ko. | There will be strong winds tonight. Secure your shelter. | sample_02.wav |
| Mwaŋi ŋʼalosyek kɨ ityo. Mɨ kɨ lor. | Flooding is dangerous. Do not cross the river. | sample_03.wav |
| Koŋ ŋʼiwɨrwɨr. Terer kɨ awi ko, lak ko. | A storm is approaching. Stay inside and keep safe. | sample_04.wav |
| Lor koŋ kɨ ngʼwan. Terer poghoi kɨ mwoi. | The river is rising fast. Take the children to safety. | sample_05.wav |
Intended Use
Speech synthesis for Pokoot East weather and emergency-alert messages. Not intended for speaker identification or any processing of personal data.
Limitations
- Fine-tuned only on the Pokoot East speech dataset; out-of-vocabulary or code-switched text may produce degraded output.
- Model inherits any biases present in the base MMS-TTS checkpoint and training data.
License
cc-by-nc-4.0 license.
Training data: see dataset card for speedykom-group/pokoot-east-speech-dataset.
- Task
- Text-to-Speech
- Type
- vits
- License
- cc-by-nc-4.0
- Created
- Apr 30, 2026
- Updated
- May 4, 2026