How is the consolidated.safetensors model file generated?
#44 opened about 2 months ago
by
deanD
Bad transcription result when using mps i.e. apple hardware acceleration
1
#43 opened 3 months ago
by
TschonnyCache
Has the model's training code been open-sourced?
2
#42 opened 3 months ago
by
desir7e
my suggestions after evaluation
1
#41 opened 3 months ago
by
Hansen-Wu
Why the weight did not match between transformers version and mistral version?
1
#40 opened 3 months ago
by
fahadh4ilyas
Clarification regarding model architecture
2
#39 opened 3 months ago
by
sovitrath
Request for open sourcing evaluation code --- at least for librispeech
5
#38 opened 3 months ago
by
sovitrath
obtain timestamps in transcription mode
π
π
8
2
#35 opened 3 months ago
by
hanifanggawi
vllm import error
#32 opened 4 months ago
by
xkzhang
Upload 10-MB-Test (1).docx
#29 opened 4 months ago
by
deleted
Upload 1-MB-Test.xlsx
#28 opened 4 months ago
by
deleted
Upload 1mb-examplefile-com.txt
#27 opened 4 months ago
by
deleted
Offline interactive web interface for Voxtral
π€
π₯
4
#26 opened 4 months ago
by
khalooei
tokenizer.json + tokenizer_config.json missing?
2
#25 opened 4 months ago
by
am17an
correct typo in apply_transcription_request
1
#24 opened 4 months ago
by
revvvxx
Could not load symbol cudnnGetLibConfig
π
3
1
#23 opened 4 months ago
by
rareson168
Fine tuning of Model
3
#22 opened 4 months ago
by
amritansh
Adapters for Voxtral Models?
#21 opened 4 months ago
by
dinesh-001
Really appreciate the work you put into this.π€
π
1
#20 opened 4 months ago
by
deep-div
Available Gradio with VAD and diarization π
4
#19 opened 4 months ago
by
0livi3r
Update model card with paper link and library details
#18 opened 4 months ago
by
nielsr
test
#17 opened 4 months ago
by
ravivarmai
Surprisingly Good for 3B β But Not Perfect
8
#15 opened 4 months ago
by
Hussain2050
Regarding the PyTorch version used for this model
1
#6 opened 4 months ago
by
Lqqs
Colab notebook request
π
2
3
#5 opened 4 months ago
by
ritheshSree
Does this model support streaming ASR recognition, or are there any plans to open-source a streaming model?
π
4
1
#4 opened 4 months ago
by
Qoboty
Local Installation Video and Testing - Step by Step
π
4
#3 opened 4 months ago
by
fahdmirzac
Finetuning / Training
π
11
9
#1 opened 4 months ago
by
Jamie762