Aller au contenu
ModelPrésentéExterne
Télécharger

Whisper Small Te

This model was created from the Mozilla.ai Blueprint: speech-to-text-finetune.

Sourcehuggingface.co/yeshu-09/whisper-small-te/tree/2af485498f855fc040a3f0fa1fcf07626ba21fe8
TypeText modelModèle de baseopenai/whisper-smallVersionmodel

Source du modèle

Type
Text model
Taille du fichier
922 MB
Modèle de base
openai/whisper-small
Version
vmodel
Mis à jour
22 sept. 2026
Téléchargements
5
Source
Hugging Face

Description de la source

Finetuned openai/whisper-small on 123 telugu training audio samples from AkCodes23/sarvam-tts-in-te-en.

This model was created from the Mozilla.ai Blueprint: speech-to-text-finetune.

Evaluation results on 8 audio samples of telugu:

Baseline model (before finetuning) on telugu

  • Word Error Rate (Normalized): 109.73
  • Word Error Rate (Orthographic): 124.413
  • Character Error Rate (Normalized): 72.428
  • Character Error Rate (Orthographic): 98.127
  • Loss: 1.815

Finetuned model (after finetuning) on telugu

  • Word Error Rate (Normalized): 66.126
  • Word Error Rate (Orthographic): 90.141
  • Character Error Rate (Normalized): 51.045
  • Character Error Rate (Orthographic): 59.465
  • Loss: 0.597

Sources

1 source
Hugging FacePrincipalVersion 2af485498f855fc040a3f0fa1fcf07626ba21fe8
huggingface.co/yeshu-09/whisper-small-te/tree/2af485498f855fc040a3f0fa1fcf07626ba21fe8

Vérifié 22 sept.

Artefacts du modèle

1 artefact

model.safetensors

safetensors · 922 MB · SHA-256 4731b5aa07be…04dc · Hugging Face

Télécharger

Extraits de sources

2 extraits
Readme22 sept.huggingface.co/yeshu-09/whisper-small-te

--- base_model: openai/whisper-small datasets: - sarvam-tts-in-te-en language: te library_name: transformers license: apache-2.0 model-index: - name: Finetuned openai/whisper-small on telugu results: - task: type: automatic-speech-recognition name: Speech-to-Text dataset: name: Common Voice (telugu) type: common_voice metrics: - type: wer value: 66.126 --- # Finetuned openai/whisper-small on 123 telugu training audio samples from AkCodes23/sarvam-tts-in-te-en. This model was created from the Mozilla.ai Blueprint: [speech-to-text-finetune](https://github.com/mozilla-ai/speech-to-text-finetune). ## Evaluation results on 8 audio samples of telugu: ### Baseline model (before finetuning) on telugu - Word Error Rate (Normalized): 109.73 - Word Error Rate (Orthographic): 124.413 - Character Error Rate (Normalized): 72.428 - Character Error Rate (Orthographic): 98.127 - Loss: 1.815 ### Finetuned model (after finetuning) on telugu - Word Error Rate (Normalized): 66.126 - Word Error Rate (Orthographic): 90.141 - Character Error Rate (Normalized): 51.045 - Character Error Rate (Orthographic): 59.465 - Loss: 0.597

Note22 sept.huggingface.co/yeshu-09/whisper-small-te

Source context: 5 downloads · 0 likes · Pipeline automatic-speech-recognition · Library transformers · Repo yeshu-09/whisper-small-te