Downloads · 30 days
53
11% of all-time downloads
liodon-ai/vakyansh-wav2vec2-tamil-tam-250-GGUF
vakyansh-wav2vec2-tamil-tam-250-GGUF is a machine learning model from liodon-ai. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for wav2vec2.cpp. The card lists the license as other.
GGUF quantizations of Harveenchadha/vakyansh-wav2vec2-tamil-tam-250 for use with wav2vec2.cpp.
Downloads · 30 days
53
11% of all-time downloads
All-time downloads
482
Public
Repo size
400 MB
Likes
0
Public
Click a slice to open those files.
.gguf400 MB · 100%
From the Hugging Face model README
GGUF quantizations of Harveenchadha/vakyansh-wav2vec2-tamil-tam-250 for use with wav2vec2.cpp.
| Filename | Quant | Size | Precision |
|---|---|---|---|
model_f16.gguf | F16 | 189 MB | ~fp16 (near-lossless) |
model_q8_0.gguf | Q8_0 | 127 MB | 8-bit quantized linear layers |
model_q4_0.gguf | Q4_0 | 84 MB | 4-bit quantized linear layers |
Tested on 10 audio samples from FLEURS ta_in.
| Quant | Mean CER (vs HF) | Mean WER (vs HF) | Status |
|---|---|---|---|
| F16 | 0.17% | 1.20% | PASS |
| Q8_0 | 0.23% | 2.16% | PASS |
| Q4_0 | 1.64% | 13.52% | PASS |
CER/WER measured against HF model output (not ground truth) to isolate quantization error.
# Clone and build
git clone --recursive https://github.com/liodon-ai/wav2vec2.cpp
cd wav2vec2.cpp && mkdir build && cd build && cmake .. && make -j
# Download and run
huggingface-cli download liodon-ai/vakyansh-wav2vec2-tamil-tam-250-GGUF model_q8_0.gguf --local-dir .
./wav2vec2-cli -m model_q8_0.gguf -f audio.wav
# With word timestamps
./wav2vec2-cli -m model_q8_0.gguf -f audio.wav -w
# SRT subtitle output
./wav2vec2-cli -m model_q8_0.gguf -f audio.wav --format srt > output.srt
import subprocess, json
result = subprocess.run(
['./wav2vec2-cli', '-m', 'model_q8_0.gguf', '-f', 'audio.wav', '--format', 'json'],
capture_output=True, text=True
)
data = json.loads(result.stdout)
print(data['transcript'])
Converted using wav2vec2.cpp scripts/convert_to_gguf.py.
python scripts/convert_to_gguf.py Harveenchadha/vakyansh-wav2vec2-tamil-tam-250 model_f16.gguf --dtype f16
python scripts/convert_to_gguf.py Harveenchadha/vakyansh-wav2vec2-tamil-tam-250 model_q8_0.gguf --dtype q8_0
python scripts/convert_to_gguf.py Harveenchadha/vakyansh-wav2vec2-tamil-tam-250 model_q4_0.gguf --dtype q4_0
Follows the license of the source model.