Skip to content
ModelListedExternal
Download

Cey 25 Mms Tts Mozilla Gej

Fine-tuned facebook/mms-tts-gej on Mozilla Data Collective data for Mina (Gen) (gej).

Sourcehuggingface.co/Umbaji/cey-25-mms-tts-mozilla-gej/tree/ea4f86fb365f482dae61a0293f7e21fc2dbc8c7e
KindOtherBase modelfacebook/mms-tts-gejVersionRevision ea4f86f

Model source

Kind
Other
File size
139 MB
Base model
facebook/mms-tts-gej
Version
vRevision ea4f86f
Updated
Sep 22, 2026
Downloads
23
Tasks
Audio
Source
Hugging Face

Source description

MMS-TTS Mina (Gen) — Mozilla Fine-tuned

Fine-tuned facebook/mms-tts-gej on Mozilla Data Collective data for Mina (Gen) (gej).

Training Statistics

MetricValue
Training samples16966
Validation samples2995
Best val mel-L13.5964
Dataset sourceMozilla Data Collective

Usage

from transformers import VitsModel, VitsTokenizer
import torch, torchaudio

model = VitsModel.from_pretrained("Umbaji/cey-25-mms-tts-mozilla-gej")
tokenizer = VitsTokenizer.from_pretrained("Umbaji/cey-25-mms-tts-mozilla-gej")

inputs = tokenizer("your text here", return_tensors="pt")
with torch.no_grad():
    waveform = model(**inputs).waveform[0]

torchaudio.save("out.wav", waveform.unsqueeze(0), model.config.sampling_rate)

Training

  • Loss: Mel-spectrogram L1
  • Optimizer: AdamW (lr=2e-4, betas=(0.8, 0.99))
  • Scheduler: ExponentialLR γ=0.999
  • Epochs: 1 | Effective batch: 16

Fine-tuned: 2026-06-12 — Mozilla Data Collective + Eyaa-Tom

Sources

1 source
Hugging FacePrimaryVersion ea4f86fb365f482dae61a0293f7e21fc2dbc8c7e
huggingface.co/Umbaji/cey-25-mms-tts-mozilla-gej/tree/ea4f86fb365f482dae61a0293f7e21fc2dbc8c7e

Verified Sep 22

Model artifacts

1 artifact

model.safetensors

safetensors · 139 MB · SHA-256 5fc2df340000…5d49 · Hugging Face

Download

Source excerpts

2 excerpts
ReadmeSep 22huggingface.co/Umbaji/cey-25-mms-tts-mozilla-gej

--- language: - gej tags: - text-to-speech - mms-tts - vits - gej - west-africa - mozilla-data-collective - finetuned license: cc-by-nc-4.0 base_model: facebook/mms-tts-gej pipeline_tag: text-to-speech --- # MMS-TTS Mina (Gen) — Mozilla Fine-tuned Fine-tuned [facebook/mms-tts-gej](https://huggingface.co/facebook/mms-tts-gej) on Mozilla Data Collective data for **Mina (Gen)** (`gej`). ## Training Statistics | Metric | Value | |--------|-------| | Training samples | 16966 | | Validation samples | 2995 | | Best val mel-L1 | 3.5964 | | Dataset source | Mozilla Data Collective | ## Usage ```python from transformers import VitsModel, VitsTokenizer import torch, torchaudio model = VitsModel.from_pretrained("Umbaji/cey-25-mms-tts-mozilla-gej") tokenizer = VitsTokenizer.from_pretrained("Umbaji/cey-25-mms-tts-mozilla-gej") inputs = tokenizer("your text here", return_tensors="pt") with torch.no_grad(): waveform = model(**inputs).waveform[0] torchaudio.save("out.wav", waveform.unsqueeze(0), model.config.sampling_rate) ``` ## Training - **Loss**: Mel-spectrogram L1 - **Optimizer**: AdamW (lr=2e-4, betas=(0.8, 0.99)) - **Scheduler**: ExponentialLR γ=0.999 - **Epochs**: 1 | **Effective batch**: 16 *Fine-tuned: 2026-06-12 — Mozilla Data Collective + Eyaa-Tom*

NoteSep 22huggingface.co/Umbaji/cey-25-mms-tts-mozilla-gej

Source context: 23 downloads · 0 likes · Pipeline text-to-speech · Repo Umbaji/cey-25-mms-tts-mozilla-gej