Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Local wisper #1091

Closed
wants to merge 20 commits into from
Closed

Local wisper #1091

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
20 commits
Select commit Hold shift + click to select a range
1f05fdf
correcting scroll & chat response view better code
aadityamundhalia Aug 16, 2023
511a1c2
temp workign wisper
aadityamundhalia Aug 18, 2023
631b325
added wisper
aadityamundhalia Aug 30, 2023
c9af7be
added wisper
aadityamundhalia Aug 30, 2023
35f2c83
wisper
aadityamundhalia Aug 31, 2023
76498fc
working model wisper
aadityamundhalia Aug 31, 2023
87669e8
resolved delete
aadityamundhalia Aug 31, 2023
093db0e
enable_summarization
aadityamundhalia Aug 31, 2023
2ad3299
writing tests
aadityamundhalia Sep 1, 2023
e9cddf1
wisper local option
aadityamundhalia Sep 1, 2023
ab29792
added wisper in requirements.txt
aadityamundhalia Sep 1, 2023
4984e41
removed commented out code
aadityamundhalia Sep 1, 2023
f8733f7
reverted typescript
aadityamundhalia Sep 1, 2023
60ff077
removed deleted file
aadityamundhalia Sep 1, 2023
df4ae3d
Added gpu support to the docker
aadityamundhalia Sep 2, 2023
1beda7a
corrected spelling and merged transcript file
aadityamundhalia Sep 4, 2023
0d333aa
removed unused comment
aadityamundhalia Sep 4, 2023
1484d38
unused comments
aadityamundhalia Sep 4, 2023
a6cb4fa
Name update in template
aadityamundhalia Sep 4, 2023
b3539fe
resolving issue with string pattern
aadityamundhalia Sep 7, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
working model wisper
  • Loading branch information
@aadityamundhalia
aadityamundhalia committed Sep 4, 2023
commit 76498fc3d973380ad383e5b21f5ea49d6ad29628
1 change: 1 addition & 0 deletions .backend_env.example
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,6 +15,7 @@ MAX_BRAIN_PER_USER=5
#Private LLM Variables
PRIVATE=False
MODEL_PATH=./local_models/ggml-gpt4all-j-v1.3-groovy.bin
WISPER_LOCAL=True
gozineb marked this conversation as resolved.
Show resolved Hide resolved

#RESEND
RESEND_API_KEY=<change-me>
Expand Down
1 change: 1 addition & 0 deletions backend/models/settings.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,6 +23,7 @@ class BrainSettings(BaseSettings):
class LLMSettings(BaseSettings):
private: bool = False
model_path: str = "./local_models/ggml-gpt4all-j-v1.3-groovy.bin"
wisper_local: bool = True


def get_supabase_client() -> Client:
Expand Down
5 changes: 1 addition & 4 deletions backend/parsers/wisper.py
View file
Open in desktop
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Rename to whisper with an h

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

done

gozineb marked this conversation as resolved.
Show resolved Hide resolved
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,6 @@
from langchain.schema import Document
from langchain.text_splitter import RecursiveCharacterTextSplitter
from models import Brain, File
from models.settings import get_documents_vector_store
from utils.file import compute_sha1_from_content
from utils.vectors import Neurons

Expand All @@ -19,8 +18,7 @@ async def process_wisper(
temp_filename = None
file_sha = ""
dateshort = time.strftime("%Y%m%d-%H%M%S")
file_meta_name = f"txt/audiotranscript_{dateshort}.txt"
documents_vector_store = get_documents_vector_store()
file_meta_name = f"txt/audiotranscript_{file.file.filename}_{dateshort}.txt"
model = whisper.load_model("base")

try:
Expand Down Expand Up @@ -74,7 +72,6 @@ async def process_wisper(
for text in texts
]

# documents_vector_store.add_documents(docs_with_metadata)
for doc in docs_with_metadata: # pyright: ignore reportPrivateUsage=none
neurons = Neurons()
created_vector = neurons.create_vector(doc, user_openai_api_key)
Expand Down
4 changes: 2 additions & 2 deletions backend/utils/processors.py
View file
Open in desktop
gozineb marked this conversation as resolved.
Show resolved Hide resolved
Original file line number Diff line number Diff line change
Expand Up @@ -21,7 +21,7 @@
".md": process_markdown,
".markdown": process_markdown,
".m4a": process_audio,
".mp3": process_audio,
".mp3": process_wisper,
".webm": process_audio,
".mp4": process_wisper,
".mpga": process_audio,
Expand Down Expand Up @@ -52,7 +52,7 @@ async def filter_file(
):
await file.compute_file_sha1()

# print("file sha1", file.file_sha1)
print("file sha1", file.file_sha1)
file_exists = file.file_already_exists()
file_exists_in_brain = file.file_already_exists_in_brain(brain_id)

Expand Down