ModelPublicadoExterno

Balochi TTS Three Speakers

Balochi Latin-script text-to-speech with three speaker voices, built with SpeechT5.

Fuentehuggingface.co/Aynkader/Balochi-TTS-Three-Speakers/tree/cc25ef69be28788d3add9366b9144aee4e6b6a27

TipoText modelVersiónmodelBcalidad

Fuente del modelo

Tipo: Text model
Tamaño del archivo: 551 MB
Versión: vmodel
Actualizado: 26 oct 2026
Descargas: 29
Fuente: Hugging Face

Descripción de la fuente

Balochi-TTS-Three-Speakers

Balochi Latin-script text-to-speech with three speaker voices, built with SpeechT5.

Author: Aynkader
Model ID: Aynkader/Balochi-TTS-Three-Speakers
Base: Fine-tuned from BalochiT5-Fine-Tuned-Model2-News
Vocoder: microsoft/speecht5_hifigan
Training data: 75 clips (25 per speaker, shared transcripts)
Web demo: Aynkader/Balochi-TTS

Speakers

Voice	Key	Embedding file	Description
Ayn Káder	`ayn_kader`	`speaker_embedding_ayn_kader.pt`	Original news reader
Dódá	`doda`	`speaker_embedding_doda.pt`	Male voice
Dódén	`doden`	`speaker_embedding_doden.pt`	Female voice

Quick start

import torch
import soundfile as sf
from huggingface_hub import hf_hub_download
from transformers import SpeechT5ForTextToSpeech, SpeechT5HifiGan, SpeechT5Processor

MODEL_ID = "Aynkader/Balochi-TTS-Three-Speakers"
device = "cuda" if torch.cuda.is_available() else "cpu"

processor = SpeechT5Processor.from_pretrained(MODEL_ID)
model = SpeechT5ForTextToSpeech.from_pretrained(MODEL_ID).to(device).eval()
vocoder = SpeechT5HifiGan.from_pretrained("microsoft/speecht5_hifigan").to(device).eval()

emb_path = hf_hub_download(MODEL_ID, "speaker_embedding_ayn_kader.pt")
speaker = torch.load(emb_path, map_location="cpu", weights_only=False)
if speaker.dim() == 1:
    speaker = speaker.unsqueeze(0)

text = "Gwáderá tyáb dapá sharábay proshtagén bótalán daryáward paréshán kotagant."
inputs = processor(text=text, return_tensors="pt").to(device)

with torch.no_grad():
    speech = model.generate_speech(
        inputs["input_ids"],
        speaker.to(device),
        vocoder=vocoder,
        threshold=0.62,
        minlenratio=0.10,
        maxlenratio=6.0,
    )

sf.write("output.wav", speech.cpu().numpy(), 16000)

Supported text

Use Balochi Latin characters:

a b c d e g h i j k l m n o p r s t u w y z
á é ó  (and uppercase)
. , : ? ! ' -
digits 0-9

Arabic script input is supported in the web Space via built-in Arabic → Latin conversion.

Model files

File	Description
`config.json`	SpeechT5 architecture
`model.safetensors`	Fine-tuned weights (~578 MB)
`preprocessor_config.json`	Mel spectrogram settings
`spm_char.model`	SentencePiece tokenizer
`speaker_embedding_ayn_kader.pt`	News reader embedding
`speaker_embedding_doda.pt`	Male speaker embedding
`speaker_embedding_doden.pt`	Female speaker embedding

Training

Base: BalochiT5-Fine-Tuned-Model2-News (25 news clips)
Three-speaker fine-tune: 75 samples (Ayn Káder, Dódá, Dódén)
Per-file speaker embeddings (x-vector)
Script: train_tts_three_speakers.py in the upstream TTS project

Limitations

Best for short paragraphs (≤100 characters recommended)
Latin script input for direct inference; Arabic via converter
Requires internet on first run for HiFi-GAN vocoder
Small per-speaker dataset (25 clips each)

Citation

Aynkader/Balochi-TTS-Three-Speakers — https://huggingface.co/Aynkader/Balochi-TTS-Three-Speakers

License

Apache 2.0

Fuentes

1 fuente

Hugging FacePrincipalVersión cc25ef69be28788d3add9366b9144aee4e6b6a27

huggingface.co/Aynkader/Balochi-TTS-Three-Speakers/tree/cc25ef69be28788d3add9366b9144aee4e6b6a27

Verificado 26 oct

Artefactos del modelo

1 artefacto

model.safetensors

safetensors · 551 MB · SHA-256 b0497146517e…910f · Hugging Face

Download file

Extractos de fuentes

3 extractos

Readme7 agohuggingface.co/Aynkader/Balochi-TTS-Three-Speakers

--- license: apache-2.0 language: - bal tags: - text-to-speech - balochi - speecht5 - latin-script - multi-speaker library_name: transformers pipeline_tag: text-to-speech --- # Balochi-TTS-Three-Speakers Balochi **Latin-script** text-to-speech with **three speaker voices**, built with [SpeechT5](https://huggingface.co/docs/transformers/model_doc/speecht5). - **Author:** [Aynkader](https://huggingface.co/Aynkader) - **Model ID:** `Aynkader/Balochi-TTS-Three-Speakers` - **Base:** Fine-tuned from `BalochiT5-Fine-Tuned-Model2-News` - **Vocoder:** [`microsoft/speecht5_hifigan`](https://huggingface.co/microsoft/speecht5_hifigan) - **Training data:** 75 clips (25 per speaker, shared transcripts) - **Web demo:** [`Aynkader/Balochi-TTS`](https://huggingface.co/spaces/Aynkader/Balochi-TTS) ## Speakers | Voice | Key | Embedding file | Description | |-------|-----|----------------|-------------| | Ayn Káder | `ayn_kader` | `speaker_embedding_ayn_kader.pt` | Original news reader | | Dódá | `doda` | `speaker_embedding_doda.pt` | Male voice | | Dódén | `doden` | `speaker_embedding_doden.pt` | Female voice | ## Quick start ```python import torch import soundfile as sf from huggingface_hub import hf_hub_download from transformers import SpeechT5ForTextToSpeech, SpeechT5HifiGan, SpeechT5Processor MODEL_ID = "Aynkader/Balochi-TTS-Three-Speakers" device = "cuda" if torch.cuda.is_available() else "cpu" processor = SpeechT5Processor.from_pretrained(MODEL_ID) model = SpeechT5ForTextToSpeech.from_pretrained(MODEL_ID).to(device).eval() vocoder = SpeechT5HifiGan.from_pretrained("microsoft/speecht5_hifigan").to(device).eval() emb_path = hf_hub_download(MODEL_ID, "speaker_embedding_ayn_kader.pt") speaker = torch.load(emb_path, map_location="cpu", weights_only=False) if speaker.dim() == 1: speaker = speaker.unsqueeze(0) text = "Gwáderá tyáb dapá sharábay proshtagén bótalán daryáward paréshán kotagant." inputs = processor(text=text, return_tensors="pt").to(device) with torch.no_grad(): speech = model.generate_speech( inputs["input_ids"], speaker.to(device), vocoder=vocoder, threshold=0.62, minlenratio=0.10, maxlenratio=6.0, ) sf.write("output.wav", speech.cpu().numpy(), 16000) ``` ## Supported text Use **Balochi Latin** characters: ``` a b c d e g h i j k l m n o p r s t u w y z á é ó (and uppercase) . , : ? ! ' - digits 0-9 ``` Arabic script input is support...

Note26 octhuggingface.co/Aynkader/Balochi-TTS-Three-Speakers

Source context: 29 downloads · 0 likes · Pipeline text-to-speech · Library transformers · Repo Aynkader/Balochi-TTS-Three-Speakers

Note7 agohuggingface.co/Aynkader/Balochi-TTS-Three-Speakers

Source context: 101 downloads · 0 likes · Pipeline text-to-speech · Library transformers · Repo Aynkader/Balochi-TTS-Three-Speakers