github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 08:02:14 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #2815] Adding Whisper by creating Modelfile #48220

New Issue
Closed
opened 2026-04-28 07:13:58 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-28 07:13:58 -05:00
Owner
Copy Link

Originally created by @serban-razvan-termene on GitHub (Feb 28, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/2815

Ollama uses a format for the Modelfile that is described here. The Modelfile allows only for text input to be put into the resulting model.

There is one multimodal model (LLaVA) that you guys added to the model hub that uses something else other than text. But some modifications to the Ollama and the model were done. As far as I understand, the model takes the encoded image as a text parameter.

Is there any possibility for me to write a Modelfile and modify the base repository for Ollama to take audio as input for the Whisper model that takes audio as the input and outputs the text heard in that audio?

Originally created by @serban-razvan-termene on GitHub (Feb 28, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/2815 Ollama uses a format for the Modelfile that is described [here](https://github.com/ollama/ollama/blob/main/docs/modelfile.md). The Modelfile allows only for text input to be put into the resulting model. There is one multimodal model (LLaVA) that you guys added to the model hub that uses something else other than text. But some modifications to the Ollama and the model [were done](https://github.com/ollama/ollama/issues/746). As far as I understand, the model takes the encoded image as a text parameter. Is there any possibility for me to write a Modelfile and modify the base repository for Ollama to take audio as input for the Whisper model that takes audio as the input and outputs the text heard in that audio?
GiteaMirror commented 2026-04-28 07:14:00 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (May 10, 2024):

Hi @serban-razvan-termene love this idea, however not yet since Ollama doesn't support audio models yet. I'll merge this with #1168

<!-- gh-comment-id:2103679675 --> @jmorganca commented on GitHub (May 10, 2024): Hi @serban-razvan-termene love this idea, however not yet since Ollama doesn't support audio models yet. I'll merge this with #1168
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#48220
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?