Downloads · 30 days
46
4% of all-time downloads
speecht5_finetuned_hy
Edmon02/speecht5_finetuned_hy
speecht5_finetuned_hy is a text-to-speech model from Edmon02. Use it when you need text read aloud. It is set up for transformers. The card lists the license as mit.
First fine-tune of microsoft/speecht5tts on Common Voice 11 (multilingual tags: hy, en, nl). Vocab 81.
All-time downloads
1K
Public
Parameters
144M
20.8 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors578 MB · 100%
At a glance
- Task
- Text-to-Speech
- Library
- transformers
- License
- mit
- Model type
- speecht5
- Access
- Public
- Created
- Dec 7, 2023
- Updated
- Jun 4, 2026
- SHA
- 8cb30607
Base models
Model card
From the Hugging Face model README
Archived baseline: speecht5_finetuned_hy
First fine-tune of microsoft/speecht5_tts on Common Voice 11 (multilingual tags: hy, en, nl). Vocab 81.
Status
Archived — kept for lineage reproducibility. Armenian production work moved to HyVoxPopuli-based checkpoints.
Successor chain
speecht5_finetuned_hy (this repo)
→ speecht5_finetuned_voxpopuli_nl
→ speecht5_finetuned_voxpopuli_hy ← production
→ TTS_NB_2 ← active training
Evaluation (historical)
| Step | Validation loss |
|---|---|
| 1000 | 0.4785 |
Training hyperparameters
- Learning rate: 1e-5
- Effective batch size: 32
- Training steps: 1000
- Transformers 4.35.2, PyTorch 2.1.0
Use instead
| Task | Model |
|---|---|
| Armenian TTS | Edmon02/speecht5_finetuned_voxpopuli_hy |
| Fine-tuning | Edmon02/TTS_NB_2 |
License
MIT
- Task
- Text-to-Speech
- Library
- transformers
- Type
- speecht5
- License
- mit
- Languages
- hy, en, nl
- Created
- Dec 7, 2023
- Updated
- Jun 4, 2026