Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# Cosmobillian / turkish_whisper_for_noisy_datas
|
| 2 |
|
| 3 |
> A Whisper-large-v3 model fine-tuned for **noisy Turkish speech recognition** (short utterances, real-world environments).
|
|
@@ -163,4 +172,4 @@ AUDIO_PATH = "/content/uzun_kayit.wav"
|
|
| 163 |
full_text = chunked_transcribe(AUDIO_PATH, chunk_sec=30, stride_sec=5, max_new_tokens=256)
|
| 164 |
|
| 165 |
print("Tam transkripsiyon:\n")
|
| 166 |
-
print(full_text)
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- tr
|
| 4 |
+
base_model:
|
| 5 |
+
- openai/whisper-large-v3
|
| 6 |
+
pipeline_tag: automatic-speech-recognition
|
| 7 |
+
tags:
|
| 8 |
+
- turkish
|
| 9 |
+
---
|
| 10 |
# Cosmobillian / turkish_whisper_for_noisy_datas
|
| 11 |
|
| 12 |
> A Whisper-large-v3 model fine-tuned for **noisy Turkish speech recognition** (short utterances, real-world environments).
|
|
|
|
| 172 |
full_text = chunked_transcribe(AUDIO_PATH, chunk_sec=30, stride_sec=5, max_new_tokens=256)
|
| 173 |
|
| 174 |
print("Tam transkripsiyon:\n")
|
| 175 |
+
print(full_text)
|