Aller au contenu
ModelPrésentéExterne
Télécharger

Indic5

This is a fine-tuned version of ai4bharat/IndicF5 optimized for high-quality, natural Tamil speech synthesis and zero-shot voice cloning.

Sourcehuggingface.co/ragunath-ravi/indic5/tree/b37f2669446d85f810fc892fb98b4438d5937420
TypeOtherVersionRevision b37f266BClasse

Source du modèle

Type
Other
Taille du fichier
3,60 GB
Version
vRevision b37f266
Mis à jour
26 oct. 2026
Téléchargements
506
Source
Hugging Face

Description de la source

IndicF5 Tamil Fine-Tuned Model

This is a fine-tuned version of ai4bharat/IndicF5 optimized for high-quality, natural Tamil speech synthesis and zero-shot voice cloning.

Model Details

  • Base Model: ai4bharat/IndicF5
  • Fine-Tuning Dataset: TamilVoiceCorpus (PureVox split)
  • Fine-Tuning Method: Adapter-style training (Transformer backbone frozen, text embedding and projection layers updated)
  • Language: Tamil (ta)

Files Included

  • model_last.pt: Fine-tuned PyTorch checkpoint.
  • vocab.txt: Character vocabulary mapping generated from the Tamil dataset.

Sources

1 source
Hugging FacePrincipalVersion b37f2669446d85f810fc892fb98b4438d5937420
huggingface.co/ragunath-ravi/indic5/tree/b37f2669446d85f810fc892fb98b4438d5937420

Vérifié 26 oct.

Artefacts du modèle

1 artefact

model_last.pt

pt · 3,60 GB · SHA-256 7b8fec7a20a0…b4e4 · Hugging Face

Download file

Extraits de sources

3 extraits
Readme7 aoûthuggingface.co/ragunath-ravi/indic5

--- license: apache-2.0 tags: - text-to-speech - audio - voice-cloning - tamil - f5-tts - indicf5 --- # IndicF5 Tamil Fine-Tuned Model This is a fine-tuned version of `ai4bharat/IndicF5` optimized for high-quality, natural Tamil speech synthesis and zero-shot voice cloning. ## Model Details - **Base Model**: `ai4bharat/IndicF5` - **Fine-Tuning Dataset**: `TamilVoiceCorpus` (PureVox split) - **Fine-Tuning Method**: Adapter-style training (Transformer backbone frozen, text embedding and projection layers updated) - **Language**: Tamil (ta) ## Files Included - `model_last.pt`: Fine-tuned PyTorch checkpoint. - `vocab.txt`: Character vocabulary mapping generated from the Tamil dataset.

Note26 oct.huggingface.co/ragunath-ravi/indic5

Source context: 506 downloads · 0 likes · Pipeline text-to-speech · Library f5-tts · Repo ragunath-ravi/indic5

Note7 aoûthuggingface.co/ragunath-ravi/indic5

Source context: 34 downloads · 0 likes · Pipeline text-to-speech · Library f5-tts · Repo ragunath-ravi/indic5